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

[PATCH net-next v3] af_unix: pass pidfd flags via SCM_PIDFD cmsg

by Stas Sergeev

Currently SCM_PIDFD cmsg cannot be sent via unix socket (returns -EINVAL) and SO_PASSPIDFD doesn't support flags. The created pidfd always has flags set to 0. This patch implements SCM_PIDFD cmsg in AF_UNIX socket, which can be used to send flags to SO_PASSPIDFD-enabled recipient. Self-test is added for the propagation of PIDFD_NONBLOCK flag. This is mainly needed for the future extensions, like eg this one: https://lore.kernel.org/lkml/8288a08e-448b-43c2-82dc-59f87d0d9072@yandex.ru… where it was suggested to try solving the supplementary groups problem with pidfd. Changes in v3: specify target tree in patch subject Changes in v2: remove flags validation in scm_pidfd_recv(), as suggested by Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: Stas Sergeev <stsp2(a)yandex.ru> 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: Simon Horman <horms(a)kernel.org> CC: Shuah Khan <shuah(a)kernel.org> CC: Christian Brauner <brauner(a)kernel.org> CC: Jens Axboe <axboe(a)kernel.dk> CC: Willem de Bruijn <willemb(a)google.com> CC: Pavel Begunkov <asml.silence(a)gmail.com> CC: Gabriel Krisman Bertazi <krisman(a)suse.de> CC: Mina Almasry <almasrymina(a)google.com> CC: Oleg Nesterov <oleg(a)redhat.com> CC: Tycho Andersen <tandersen(a)netflix.com> CC: Al Viro <viro(a)zeniv.linux.org.uk> CC: Kuniyuki Iwashima <kuniyu(a)amazon.com> CC: Gou Hao <gouhao(a)uniontech.com> CC: Abhishek Chauhan <quic_abchauha(a)quicinc.com> CC: Michal Luczaj <mhal(a)rbox.co> CC: Kees Cook <kees(a)kernel.org> CC: Aleksa Sarai <cyphar(a)cyphar.com> CC: linux-kernel(a)vger.kernel.org CC: netdev(a)vger.kernel.org CC: linux-kselftest(a)vger.kernel.org --- include/linux/pidfs.h | 9 +++ include/linux/socket.h | 2 +- include/net/af_unix.h | 1 + include/net/scm.h | 3 +- kernel/pid.c | 6 +- net/core/scm.c | 14 ++++ net/core/sock.c | 1 + net/unix/af_unix.c | 3 + .../testing/selftests/net/af_unix/scm_pidfd.c | 70 +++++++++++++++++-- 9 files changed, 99 insertions(+), 10 deletions(-) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..c4c5c1a0c2ad 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,7 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +#include <uapi/linux/pidfd.h> + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +static inline int pidfd_validate_flags(unsigned int flags) +{ + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) + return -EINVAL; + return 0; +} + #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..ee27d391e5aa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -178,7 +178,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD 0x04 /* r: pidfd, w: pidfd_flags (int) */ struct ucred { __u32 pid; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 63129c79b8cb..4bc197548c2f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_skb_parms { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif + u32 pidfd_flags; u32 consumed; } __randomize_layout; diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..1326edcacacb 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -48,6 +48,7 @@ struct scm_cookie { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Passed security ID */ #endif + u32 pidfd_flags; }; void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); @@ -154,7 +155,7 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm if (!scm->pid) return; - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + pidfd = pidfd_prepare(scm->pid, scm->pidfd_flags, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..b1100ae8ea63 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -629,10 +629,12 @@ static int pidfd_create(struct pid *pid, unsigned int flags) SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; + int err; struct pid *p; - if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) - return -EINVAL; + err = pidfd_validate_flags(flags); + if (err) + return err; if (pid <= 0) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..3bcdecdacd7e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -23,6 +23,7 @@ #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> @@ -210,6 +211,19 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->creds.gid = gid; break; } + case SCM_PIDFD: + { + unsigned int flags; + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(flags))) + goto error; + memcpy(&flags, CMSG_DATA(cmsg), sizeof(flags)); + err = pidfd_validate_flags(flags); + if (err) + goto error; + p->pidfd_flags = flags; + break; + } default: goto error; } diff --git a/net/core/sock.c b/net/core/sock.c index 039be95c40cf..d1fce437c035 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2930,6 +2930,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: + case SCM_PIDFD: break; default: return -EINVAL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..8b19dfec0221 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1892,6 +1892,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; + UNIXCB(skb).pidfd_flags = scm->pidfd_flags; unix_get_secdata(scm, skb); if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -2486,6 +2487,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); if (!(flags & MSG_PEEK)) { @@ -2873,6 +2875,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); check_creds = true; } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..1e70ff253a1d 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -5,6 +5,7 @@ #include <stddef.h> #include <stdio.h> #include <stdlib.h> +#include <fcntl.h> #include <sys/socket.h> #include <linux/socket.h> #include <unistd.h> @@ -15,6 +16,11 @@ #include <sys/types.h> #include <sys/wait.h> +/* There are problems including linux/pidfd.h, so define. */ +#ifndef PIDFD_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#endif + #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -126,7 +132,7 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } -static int cmsg_check(int fd) +static int cmsg_check(int fd, unsigned int pidfd_flags) { struct msghdr msg = { 0 }; struct cmsghdr *cmsg; @@ -136,6 +142,7 @@ static int cmsg_check(int fd) char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; int *pidfd = NULL; + unsigned int flags; pid_t parent_pid; int err; @@ -197,6 +204,13 @@ static int cmsg_check(int fd) return 1; } + flags = fcntl(*pidfd, F_GETFL, 0); + flags &= ~O_ACCMODE; + if (flags != pidfd_flags) { + log_err("SCM_PIDFD flags mismatch: %x != %x", flags, pidfd_flags); + 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); @@ -227,30 +241,49 @@ FIXTURE_VARIANT(scm_pidfd) { int type; bool abstract; + unsigned int flags; }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) { .type = SOCK_STREAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) { .type = SOCK_STREAM, .abstract = 1, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) { .type = SOCK_DGRAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) { .type = SOCK_DGRAM, .abstract = 1, + .flags = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_nonblock) +{ + .type = SOCK_STREAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_nonblock) +{ + .type = SOCK_DGRAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, }; FIXTURE_SETUP(scm_pidfd) @@ -335,7 +368,7 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, close(self->startup_pipe[1]); - if (cmsg_check(cfd)) { + if (cmsg_check(cfd, variant->flags)) { log_err("cmsg_check failed"); child_die(); } @@ -375,6 +408,27 @@ TEST_F(scm_pidfd, test) int err; int pfd; int child_status = 0; + char iobuf; + unsigned int pidfd_flags; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec io = { + .iov_base = &iobuf, + .iov_len = sizeof(iobuf) + }; + union { + char buf[CMSG_SPACE(sizeof(pidfd_flags))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_PIDFD; + cmsg->cmsg_len = CMSG_LEN(sizeof(pidfd_flags)); self->server = socket(AF_UNIX, variant->type, 0); ASSERT_NE(-1, self->server); @@ -414,12 +468,16 @@ TEST_F(scm_pidfd, test) 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); + err = connect(pfd, + (struct sockaddr *)&self->client_addr->listen_addr, + self->client_addr->addrlen); ASSERT_NE(-1, err); } + iobuf = 'x'; + pidfd_flags = variant->flags; + memcpy(CMSG_DATA(cmsg), &pidfd_flags, sizeof(pidfd_flags)); + err = sendmsg(pfd, &msg, 0); + ASSERT_NE(-1, err); close(pfd); waitpid(self->client_pid, &child_status, 0); -- 2.47.0

1 year

5
5
0 0

[PATCH v3] selftests/lam: Test get_user() LAM pointer handling

by Maciej Wieczor-Retman

Recent change in how get_user() handles pointers [1] has a specific case for LAM. It assigns a different bitmask that's later used to check whether a pointer comes from userland in get_user(). While currently commented out (until LASS [2] is merged into the kernel) it's worth making changes to the LAM selftest ahead of time. Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses get_user() in its implementation. Execute the syscall with differently tagged pointers to verify that valid user pointers are passing through and invalid kernel/non-canonical pointers are not. Code was tested on a Sierra Forest Xeon machine that's LAM capable. The test was ran without issues with both the LAM lines from [1] untouched and commented out. The test was also ran without issues with LAM_SUP both enabled and disabled. 4/5 level pagetables code paths were also successfully tested in Simics on a 5-level capable machine. [1] https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundati… [2] https://lore.kernel.org/all/20240710160655.3402786-1-alexander.shishkin@lin… Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> --- Changelog v3: - mmap the pointer passed to get_user to high address if 5 level paging is enabled and to low address if 4 level paging is enabled. Changelog v2: - Use mmap with HIGH_ADDR to check if we're in 5 or 4 level pagetables. tools/testing/selftests/x86/lam.c | 110 ++++++++++++++++++++++++++++++ 1 file changed, 110 insertions(+) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..616a523c3262 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -4,6 +4,7 @@ #include <stdlib.h> #include <string.h> #include <sys/syscall.h> +#include <sys/ioctl.h> #include <time.h> #include <signal.h> #include <setjmp.h> @@ -43,7 +44,15 @@ #define FUNC_INHERITE 0x20 #define FUNC_PASID 0x40 +/* get_user() pointer test cases */ +#define GET_USER_USER 0 +#define GET_USER_KERNEL_TOP 1 +#define GET_USER_KERNEL_BOT 2 +#define GET_USER_KERNEL 3 + #define TEST_MASK 0x7f +#define L5_SIGN_EXT_MASK (0xFFUL << 56) +#define L4_SIGN_EXT_MASK (0x1FFFFUL << 47) #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) @@ -370,6 +379,80 @@ static int handle_syscall(struct testcases *test) return ret; } +static int get_user_syscall(struct testcases *test) +{ + uint64_t ptr_address, bitmask; + void *p, *ptr; + int ret = 0; + int fd; + + p = mmap((void *)HIGH_ADDR, 1, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + + if (p == MAP_FAILED) { + bitmask = L4_SIGN_EXT_MASK; + ptr_address = LOW_ADDR; + + } else { + bitmask = L5_SIGN_EXT_MASK; + ptr_address = HIGH_ADDR; + } + + munmap(p, 1); + + ptr = mmap((void *)ptr_address, 1, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + + if (ptr == MAP_FAILED) { + perror("failed to map byte to pass into get_user"); + return 1; + } + + if (test->lam != 0) { + if (set_lam(test->lam) != 0) { + ret = 2; + goto error; + } + } + + fd = memfd_create("lam_ioctl", 0); + if (fd == -1) { + munmap(ptr, 1); + exit(EXIT_FAILURE); + } + + switch (test->later) { + case GET_USER_USER: + /* Control group - properly tagger user pointer */ + ptr = (void *)set_metadata((uint64_t)ptr, test->lam); + break; + case GET_USER_KERNEL_TOP: + /* Kernel address with top bit cleared */ + bitmask &= (bitmask >> 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL_BOT: + /* Kernel address with bottom sign-extension bit cleared */ + bitmask &= (bitmask << 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL: + /* Try to pass a kernel address */ + ptr = (void *)((uint64_t)ptr | bitmask); + break; + default: + printf("Invalid test case value passed!\n"); + break; + } + + if (ioctl(fd, FIOASYNC, ptr) != 0) + ret = 1; + +error: + munmap(ptr, 1); + return ret; +} + int sys_uring_setup(unsigned int entries, struct io_uring_params *p) { return (int)syscall(__NR_io_uring_setup, entries, p); @@ -883,6 +966,33 @@ static struct testcases syscall_cases[] = { .test_func = handle_syscall, .msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", }, + { + .later = GET_USER_USER, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n", + }, + { + .later = GET_USER_KERNEL_TOP, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n", + }, + { + .later = GET_USER_KERNEL_BOT, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n", + }, + { + .later = GET_USER_KERNEL, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n", + }, }; static struct testcases mmap_cases[] = { -- 2.46.2

1 year

2
2
0 0

[PATCH v5] Kunit to check the longest symbol length

by Sergio González Collado

The longest length of a symbol (KSYM_NAME_LEN) was increased to 512 in the reference [1]. This patch adds kunit test suite to check the longest symbol length. These tests verify that the longest symbol length defined is supported. This test can also help other efforts for longer symbol length, like [2]. The test suite defines two symbols, one with the longest length defined, and other one whit the longest length defined +1. In the test suite there are four tests, three positive and one negative. The first and third tests, verify that functions with names of the created symbols, can be called or not. The second and fourth tests, verify that the symbols are created (or not) in the kernel symbol table. [1] https://lore.kernel.org/lkml/20220802015052.10452-6-ojeda@kernel.org/ [2] https://lore.kernel.org/lkml/20240605032120.3179157-1-song@kernel.org/ Tested-by: Martin Rodriguez Reboredo <yakoyoku(a)gmail.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> Link: https://github.com/Rust-for-Linux/linux/issues/504 --- V1 -> V2: corrected CI tests. Added fix proposed at [3] [3] https://lore.kernel.org/lkml/Y9ES4UKl%2F+DtvAVS@gmail.com/T/#m3ef0e12bb834d… --- V2 -> V3: updated base and added MODULE_DESCRIPTION() and MODULE_AUTHOR() --- V3 -> V4: add x86 mantainers, add new reference. --- V4 -> V5: fixed typo, added improved description The test execution shoud result in something like: ``` [20:04:35] =============== longest-symbol (4 subtests) ================ [20:04:35] [PASSED] test_longest_symbol [20:04:35] [PASSED] test_longest_symbol_kallsyms [20:04:35] [PASSED] test_longest_symbol_plus1 [20:04:35] [PASSED] test_longest_symbol_plus1_kallsyms [20:04:35] ================= [PASSED] longest-symbol ================== [20:04:35] ============================================================ [20:04:35] Testing complete. Ran 4 tests: passed: 4 ``` But also there are two warnings like: ``` Symbol snnnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnnnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nnng1h2i3j4k5l6m7ng1h2i3j4k5l6m7nng1h2i3j4k5l6m7ng1h2i3j4k5l6m7ne too long for kallsyms (512 >= 512). Please increase KSYM_NAME_LEN both in kernel and kallsyms.c ``` Because the tests try to generate simbols of the same length as KSYM_NAME_LEN. This is the expected outcome, as defined: https://lore.kernel.org/all/20131023130753.GO29695@two.firstfloor.org/ --- arch/x86/tools/insn_decoder_test.c | 3 +- lib/Kconfig.debug | 9 +++ lib/Makefile | 2 + lib/longest_symbol_kunit.c | 125 +++++++++++++++++++++++++++++ 4 files changed, 138 insertions(+), 1 deletion(-) create mode 100644 lib/longest_symbol_kunit.c diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..3bde35ea4188 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,6 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> +#include <linux/kallsysms.h> #define unlikely(cond) (cond) @@ -106,7 +107,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7312ae7c3cc5..1f3059176637 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2820,6 +2820,15 @@ config FORTIFY_KUNIT_TEST by the str*() and mem*() family of functions. For testing runtime traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests. +config LONGEST_SYM_KUNIT_TEST + tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS + depends on KUNIT && KPROBES + default KUNIT_ALL_TESTS + help + Tests the longest symbol possible + + If unsure, say N. + config HW_BREAKPOINT_KUNIT_TEST bool "Test hw_breakpoint constraints accounting" if !KUNIT_ALL_TESTS depends on HAVE_HW_BREAKPOINT diff --git a/lib/Makefile b/lib/Makefile index 773adf88af41..fc878e716825 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -389,6 +389,8 @@ CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o +obj-$(CONFIG_LONGEST_SYM_KUNIT_TEST) += longest_symbol_kunit.o +CFLAGS_longest_symbol_kunit.o += $(call cc-disable-warning, missing-prototypes) obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/longest_symbol_kunit.c b/lib/longest_symbol_kunit.c new file mode 100644 index 000000000000..ebd26eedbf7b --- /dev/null +++ b/lib/longest_symbol_kunit.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test the longest symbol length. Execute with: + * ./tools/testing/kunit/kunit.py run longest-symbol + * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y + * --kconfig_add CONFIG_RETPOLINE=n --kconfig_add CONFIG_CFI_CLANG=n + * --kconfig_add CONFIG_MITIGATION_RETPOLINE=n + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/stringify.h> +#include <linux/kprobes.h> +#include <linux/kallsyms.h> + +#define DI(name) s##name##name +#define DDI(name) DI(n##name##name) +#define DDDI(name) DDI(n##name##name) +#define DDDDI(name) DDDI(n##name##name) +#define DDDDDI(name) DDDDI(n##name##name) + +#define PLUS1(name) __PASTE(name, e) + +/*Generate a symbol whose name length is 511 */ +#define LONGEST_SYM_NAME DDDDDI(g1h2i3j4k5l6m7n) + +/*Generate a symbol whose name length is 512 */ +#define LONGEST_SYM_NAME_PLUS1 PLUS1(LONGEST_SYM_NAME) + +#define RETURN_LONGEST_SYM 0xAAAAA +#define RETURN_LONGEST_SYM_PLUS1 0x55555 + +noinline int LONGEST_SYM_NAME(void); +noinline int LONGEST_SYM_NAME(void) +{ + return RETURN_LONGEST_SYM; +} + +noinline int LONGEST_SYM_NAME_PLUS1(void); +noinline int LONGEST_SYM_NAME_PLUS1(void) +{ + return RETURN_LONGEST_SYM_PLUS1; +} + +_Static_assert(sizeof(__stringify(LONGEST_SYM_NAME)) == KSYM_NAME_LEN, +"Incorrect symbol length found. Expected KSYM_NAME_LEN: " +__stringify(KSYM_NAME) ", but found: " +__stringify(sizeof(LONGEST_SYM_NAME))); + +static void test_longest_symbol(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, LONGEST_SYM_NAME()); +}; + +static void test_longest_symbol_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME)); + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM, longest_sym()); +}; + +static void test_longest_symbol_plus1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, RETURN_LONGEST_SYM_PLUS1, LONGEST_SYM_NAME_PLUS1()); +}; + +static void test_longest_symbol_plus1_kallsyms(struct kunit *test) +{ + unsigned long (*kallsyms_lookup_name)(const char *name); + static int (*longest_sym_plus1)(void); + + struct kprobe kp = { + .symbol_name = "kallsyms_lookup_name", + }; + + if (register_kprobe(&kp) < 0) { + pr_info("%s: kprobe not registered\n", __func__); + KUNIT_FAIL(test, "test_longest_symbol kallsysms: kprobe not registered\n"); + return; + } + + kunit_warn(test, "test_longest_symbol_plus1 kallsyms: kprobe registered\n"); + kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; + unregister_kprobe(&kp); + + longest_sym_plus1 = + (void *) kallsyms_lookup_name(__stringify(LONGEST_SYM_NAME_PLUS1)); + KUNIT_EXPECT_NULL(test, longest_sym_plus1); +}; + +static struct kunit_case longest_symbol_test_cases[] = { + KUNIT_CASE(test_longest_symbol), + KUNIT_CASE(test_longest_symbol_kallsyms), + KUNIT_CASE(test_longest_symbol_plus1), + KUNIT_CASE(test_longest_symbol_plus1_kallsyms), + {} +}; + +static struct kunit_suite longest_symbol_test_suite = { + .name = "longest-symbol", + .test_cases = longest_symbol_test_cases, +}; +kunit_test_suite(longest_symbol_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test the longest symbol length"); +MODULE_AUTHOR("Sergio González Collado"); -- 2.39.2

1 year

2
2
0 0

[PATCH net-next v4 0/5] net: Improve netns handling in RTNL and ip_tunnel

by Xiao Liang

This patch series includes some netns-related improvements and fixes for RTNL and ip_tunnel, to make link creation more intuitive: - Creating link in another net namespace doesn't conflict with link names in current one. - Refector rtnetlink link creation. Create link in target namespace directly. Pass both source and link netns to drivers via newlink() callback. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. --- v4: - Pack newlink() parameters to a single struct. - Use ynl async_msg_queue.empty() in selftest. v3: link: https://lore.kernel.org/all/20241113125715.150201-1-shaw.leon@gmail.com/ - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Xiao Liang (5): net: ip_tunnel: Build flow in underlay net namespace rtnetlink: Lookup device in target netns when creating link rtnetlink: Decouple net namespaces in rtnl_newlink_create() selftests: net: Add python context manager for netns entering selftests: net: Add two test cases for link netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 11 ++++-- drivers/net/amt.c | 13 ++++--- drivers/net/bareudp.c | 11 ++++-- drivers/net/bonding/bond_netlink.c | 8 ++-- drivers/net/can/dev/netlink.c | 4 +- drivers/net/can/vxcan.c | 11 ++++-- .../ethernet/qualcomm/rmnet/rmnet_config.c | 11 ++++-- drivers/net/geneve.c | 11 ++++-- drivers/net/gtp.c | 9 +++-- drivers/net/ipvlan/ipvlan.h | 4 +- drivers/net/ipvlan/ipvlan_main.c | 11 ++++-- drivers/net/ipvlan/ipvtap.c | 7 ++-- drivers/net/macsec.c | 11 ++++-- drivers/net/macvlan.c | 8 ++-- drivers/net/macvtap.c | 8 ++-- drivers/net/netkit.c | 11 ++++-- drivers/net/pfcp.c | 8 ++-- drivers/net/ppp/ppp_generic.c | 10 +++-- drivers/net/team/team_core.c | 7 ++-- drivers/net/veth.c | 11 ++++-- drivers/net/vrf.c | 7 ++-- drivers/net/vxlan/vxlan_core.c | 11 ++++-- drivers/net/wireguard/device.c | 8 ++-- drivers/net/wireless/virtual/virt_wifi.c | 10 +++-- drivers/net/wwan/wwan_core.c | 15 +++++-- include/net/ip_tunnels.h | 5 ++- include/net/rtnetlink.h | 34 +++++++++++++--- net/8021q/vlan_netlink.c | 11 ++++-- net/batman-adv/soft-interface.c | 8 ++-- net/bridge/br_netlink.c | 8 ++-- net/caif/chnl_net.c | 6 +-- net/core/rtnetlink.c | 29 +++++++++----- net/hsr/hsr_netlink.c | 14 ++++--- net/ieee802154/6lowpan/core.c | 9 +++-- net/ipv4/ip_gre.c | 27 ++++++++----- net/ipv4/ip_tunnel.c | 16 ++++---- net/ipv4/ip_vti.c | 10 +++-- net/ipv4/ipip.c | 10 +++-- net/ipv6/ip6_gre.c | 28 +++++++------ net/ipv6/ip6_tunnel.c | 16 ++++---- net/ipv6/ip6_vti.c | 15 ++++--- net/ipv6/sit.c | 16 ++++---- net/xfrm/xfrm_interface_core.c | 14 +++---- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++++++++ tools/testing/selftests/net/netns-name.sh | 10 +++++ tools/testing/selftests/net/netns_atomic.py | 39 +++++++++++++++++++ 48 files changed, 377 insertions(+), 205 deletions(-) create mode 100755 tools/testing/selftests/net/netns_atomic.py -- 2.47.0

1 year

3
7
0 0

[PATCH net v2 2/2] selftests: net: test extacks in netlink dumps

by Jakub Kicinski

Test that extacks in dumps work. The test fills up the receive buffer to test both the inline dump (as part of sendmsg()) and delayed one (run during recvmsg()). Use YNL helpers to parse the messages. We need to add the test to YNL file to make sure the right include path are used. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/netlink-dumps.c | 129 ++++++++++++++++++++ 2 files changed, 130 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5e86f7a51b43..c427ee32b193 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -78,7 +78,6 @@ TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash -TEST_GEN_PROGS += netlink-dumps TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_GEN_PROGS += sk_so_peek_off @@ -100,7 +99,7 @@ TEST_PROGS += bpf_offload.py # YNL files, must be before "include ..lib.mk" EXTRA_CLEAN += $(OUTPUT)/libynl.a -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := ncdevmem netlink-dumps TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_FILES := settings diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7ee6dcd334df..195febbf6a61 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -12,11 +12,140 @@ #include <unistd.h> #include <linux/genetlink.h> +#include <linux/neighbour.h> +#include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/mqueue.h> +#include <linux/rtnetlink.h> #include "../kselftest_harness.h" +#include <ynl.h> + +struct ext_ack { + int err; + + __u32 attr_offs; + __u32 miss_type; + __u32 miss_nest; + const char *str; +}; + +/* 0: no done, 1: done found, 2: extack found, -1: error */ +static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) +{ + const struct nlmsghdr *nlh; + const struct nlattr *attr; + ssize_t rem; + + for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) { + nlh = (struct nlmsghdr *)&buf[n - rem]; + if (!NLMSG_OK(nlh, rem)) + return -1; + + if (nlh->nlmsg_type != NLMSG_DONE) + continue; + + ea->err = -*(int *)NLMSG_DATA(nlh); + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 1; + + ynl_attr_for_each(attr, nlh, sizeof(int)) { + switch (ynl_attr_type(attr)) { + case NLMSGERR_ATTR_OFFS: + ea->attr_offs = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_TYPE: + ea->miss_type = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_NEST: + ea->miss_nest = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MSG: + ea->str = ynl_attr_get_str(attr); + break; + } + } + + return 2; + } + + return 0; +} + +static const struct { + struct nlmsghdr nlhdr; + struct ndmsg ndm; + struct nlattr ahdr; + __u32 val; +} dump_neigh_bad = { + .nlhdr = { + .nlmsg_len = sizeof(dump_neigh_bad), + .nlmsg_type = RTM_GETNEIGH, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + .nlmsg_seq = 1, + }, + .ndm = { + .ndm_family = 123, + }, + .ahdr = { + .nla_len = 4 + 4, + .nla_type = NDA_FLAGS_EXT, + }, + .val = -1, // should fail MASK validation +}; + +TEST(dump_extack) +{ + int netlink_sock; + char buf[8192]; + int one = 1; + int i, cnt; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + ASSERT_GE(netlink_sock, 0); + + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_CAP_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_GET_STRICT_CHK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + + /* Dump so many times we fill up the buffer */ + cnt = 64; + for (i = 0; i < cnt; i++) { + n = send(netlink_sock, &dump_neigh_bad, + sizeof(dump_neigh_bad), 0); + ASSERT_EQ(n, sizeof(dump_neigh_bad)); + } + + /* Read out the ENOBUFS */ + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + EXPECT_EQ(n, -1); + EXPECT_EQ(errno, ENOBUFS); + + for (i = 0; i < cnt; i++) { + struct ext_ack ea = {}; + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + if (n < 0) { + ASSERT_GE(i, 10); + break; + } + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); + + EXPECT_EQ(nl_get_extack(buf, n, &ea), 2); + EXPECT_EQ(ea.attr_offs, + sizeof(struct nlmsghdr) + sizeof(struct ndmsg)); + } +} + static const struct { struct nlmsghdr nlhdr; struct genlmsghdr genlhdr; -- 2.47.0

1 year

2
1
0 0

[RFC] Test catalog template

by Donald Zickus

Hi, At Linux Plumbers, a few dozen of us gathered together to discuss how to expose what tests subsystem maintainers would like to run for every patch submitted or when CI runs tests. We agreed on a mock up of a yaml template to start gathering info. The yaml file could be temporarily stored on kernelci.org until a more permanent home could be found. Attached is a template to start the conversation. Longer story. The current problem is CI systems are not unanimous about what tests they run on submitted patches or git branches. This makes it difficult to figure out why a test failed or how to reproduce. Further, it isn't always clear what tests a normal contributor should run before posting patches. It has been long communicated that the tests LTP, xfstest and/or kselftests should be the tests to run. However, not all maintainers use those tests for their subsystems. I am hoping to either capture those tests or find ways to convince them to add their tests to the preferred locations. The goal is for a given subsystem (defined in MAINTAINERS), define a set of tests that should be run for any contributions to that subsystem. The hope is the collective CI results can be triaged collectively (because they are related) and even have the numerous flakes waived collectively (same reason) improving the ability to find and debug new test failures. Because the tests and process are known, having a human help debug any failures becomes easier. The plan is to put together a minimal yaml template that gets us going (even if it is not optimized yet) and aim for about a dozen or so subsystems. At that point we should have enough feedback to promote this more seriously and talk optimizations. Feedback encouraged. Cheers, Don --- # List of tests by subsystem # # Tests should adhere to KTAP definitions for results # # Description of section entries # # maintainer: test maintainer - name <email> # list: mailing list for discussion # version: stable version of the test # dependency: necessary distro package for testing # test: # path: internal git path or url to fetch from # cmd: command to run; ability to run locally # param: additional param necessary to run test # hardware: hardware necessary for validation # # Subsystems (alphabetical) KUNIT TEST: maintainer: - name: name1 email: email1 - name: name2 email: email2 list: version: dependency: - dep1 - dep2 test: - path: tools/testing/kunit cmd: param: - path: cmd: param: hardware: none

1 year

7
16
0 0

[PATCH livepatch/master v1 1/6] selftests/livepatch: fix test-callbacks.sh execution error

by George Guo

From: George Guo <guodongtai(a)kylinos.cn> The script test-callbacks.sh fails with the following error: $ sudo ./test-callbacks.sh TEST: target module before livepatch ... not ok - expected + result test_klp_callbacks_mod: test_klp_callbacks_mod_init % insmod test_modules/test_klp_callbacks_demo.ko livepatch: enabling patch 'test_klp_callbacks_demo' -livepatch: 'test_klp_callbacks_demo': initializing patching transition +transition: 'test_klp_callbacks_demo': initializing patching transition test_klp_callbacks_demo: pre_patch_callback: vmlinux test_klp_callbacks_demo: pre_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_LIVE] Normal state -livepatch: 'test_klp_callbacks_demo': starting patching transition -livepatch: 'test_klp_callbacks_demo': completing patching transition +transition: 'test_klp_callbacks_demo': starting patching transition +transition: 'test_klp_callbacks_demo': completing patching transition test_klp_callbacks_demo: post_patch_callback: vmlinux test_klp_callbacks_demo: post_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_LIVE] Normal state -livepatch: 'test_klp_callbacks_demo': patching complete +transition: 'test_klp_callbacks_demo': patching complete % echo 0 > /sys/kernel/livepatch/test_klp_callbacks_demo/enabled -livepatch: 'test_klp_callbacks_demo': initializing unpatching transition +transition: 'test_klp_callbacks_demo': initializing unpatching transition test_klp_callbacks_demo: pre_unpatch_callback: vmlinux test_klp_callbacks_demo: pre_unpatch_callback: test_klp_callbacks_mod -> [MODULE_STATE_LIVE] Normal state -livepatch: 'test_klp_callbacks_demo': starting unpatching transition -livepatch: 'test_klp_callbacks_demo': completing unpatching transition +transition: 'test_klp_callbacks_demo': starting unpatching transition +transition: 'test_klp_callbacks_demo': completing unpatching transition test_klp_callbacks_demo: post_unpatch_callback: vmlinux test_klp_callbacks_demo: post_unpatch_callback: test_klp_callbacks_mod -> [MODULE_STATE_LIVE] Normal state -livepatch: 'test_klp_callbacks_demo': unpatching complete +transition: 'test_klp_callbacks_demo': unpatching complete % rmmod test_klp_callbacks_demo % rmmod test_klp_callbacks_mod test_klp_callbacks_mod: test_klp_callbacks_mod_exit ERROR: livepatch kselftest(s) failed The issue arises due to a mismatch in expected log output during livepatch transition. Specifically, the logs previously contained "livepatch:" but have now been updated to "transition:". This results in test failures when comparing the output with the expected values. This patch updates the expected test output to reflect the new log format. Signed-off-by: George Guo <guodongtai(a)kylinos.cn> --- .../selftests/livepatch/test-callbacks.sh | 188 +++++++++--------- 1 file changed, 94 insertions(+), 94 deletions(-) diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh index 32b150e25b10..08a33c15bb29 100755 --- a/tools/testing/selftests/livepatch/test-callbacks.sh +++ b/tools/testing/selftests/livepatch/test-callbacks.sh @@ -38,23 +38,23 @@ check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init % insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH % rmmod $MOD_TARGET $MOD_TARGET: ${MOD_TARGET}_exit" @@ -83,26 +83,26 @@ unload_mod $MOD_TARGET check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_TARGET: ${MOD_TARGET}_init % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH % rmmod $MOD_TARGET $MOD_TARGET: ${MOD_TARGET}_exit" @@ -133,26 +133,26 @@ check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init % insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % rmmod $MOD_TARGET $MOD_TARGET: ${MOD_TARGET}_exit $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going away livepatch: reverting patch '$MOD_LIVEPATCH' on unloading module '$MOD_TARGET' $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going away % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" @@ -179,12 +179,12 @@ unload_lp $MOD_LIVEPATCH check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -196,12 +196,12 @@ $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going livepatch: reverting patch '$MOD_LIVEPATCH' on unloading module '$MOD_TARGET' $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going away % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" @@ -221,19 +221,19 @@ unload_lp $MOD_LIVEPATCH check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" @@ -258,13 +258,13 @@ check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init % insmod test_modules/$MOD_LIVEPATCH.ko pre_patch_ret=-19 livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition test_klp_callbacks_demo: pre_patch_callback: vmlinux livepatch: pre-patch callback failed for object 'vmlinux' livepatch: failed to enable patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch -livepatch: '$MOD_LIVEPATCH': completing unpatching transition -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch +transition: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': unpatching complete insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: No such device % rmmod $MOD_TARGET $MOD_TARGET: ${MOD_TARGET}_exit" @@ -297,12 +297,12 @@ unload_lp $MOD_LIVEPATCH check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % echo -19 > /sys/module/$MOD_LIVEPATCH/parameters/pre_patch_ret % insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' @@ -311,12 +311,12 @@ livepatch: pre-patch callback failed for object '$MOD_TARGET' livepatch: patch '$MOD_LIVEPATCH' failed for module '$MOD_TARGET', refusing to load module '$MOD_TARGET' insmod: ERROR: could not insert module test_modules/$MOD_TARGET.ko: No such device % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH" @@ -346,14 +346,14 @@ $MOD_TARGET_BUSY: busymod_work_func enter $MOD_TARGET_BUSY: busymod_work_func exit % insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -365,14 +365,14 @@ $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going livepatch: reverting patch '$MOD_LIVEPATCH' on unloading module '$MOD_TARGET' $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going away % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux $MOD_LIVEPATCH: pre_unpatch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH % rmmod $MOD_TARGET_BUSY $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_exit" @@ -426,10 +426,10 @@ $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init $MOD_TARGET_BUSY: busymod_work_func enter % insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': starting patching transition % insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -439,12 +439,12 @@ $MOD_TARGET: ${MOD_TARGET}_exit livepatch: reverting patch '$MOD_LIVEPATCH' on unloading module '$MOD_TARGET' $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET -> [MODULE_STATE_GOING] Going away % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': reversing transition from patching to unpatching -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': reversing transition from patching to unpatching +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux $MOD_LIVEPATCH: post_unpatch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH % rmmod $MOD_TARGET_BUSY $MOD_TARGET_BUSY: busymod_work_func exit @@ -469,34 +469,34 @@ unload_lp $MOD_LIVEPATCH check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' -livepatch: '$MOD_LIVEPATCH2': initializing patching transition +transition: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': starting patching transition -livepatch: '$MOD_LIVEPATCH2': completing patching transition +transition: '$MOD_LIVEPATCH2': starting patching transition +transition: '$MOD_LIVEPATCH2': completing patching transition $MOD_LIVEPATCH2: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': patching complete +transition: '$MOD_LIVEPATCH2': patching complete % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled -livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition +transition: '$MOD_LIVEPATCH2': initializing unpatching transition $MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': starting unpatching transition -livepatch: '$MOD_LIVEPATCH2': completing unpatching transition +transition: '$MOD_LIVEPATCH2': starting unpatching transition +transition: '$MOD_LIVEPATCH2': completing unpatching transition $MOD_LIVEPATCH2: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': unpatching complete +transition: '$MOD_LIVEPATCH2': unpatching complete % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled -livepatch: '$MOD_LIVEPATCH': initializing unpatching transition +transition: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting unpatching transition -livepatch: '$MOD_LIVEPATCH': completing unpatching transition +transition: '$MOD_LIVEPATCH': starting unpatching transition +transition: '$MOD_LIVEPATCH': completing unpatching transition $MOD_LIVEPATCH: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': unpatching complete +transition: '$MOD_LIVEPATCH': unpatching complete % rmmod $MOD_LIVEPATCH2 % rmmod $MOD_LIVEPATCH" @@ -525,27 +525,27 @@ unload_lp $MOD_LIVEPATCH check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' -livepatch: '$MOD_LIVEPATCH': initializing patching transition +transition: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': starting patching transition -livepatch: '$MOD_LIVEPATCH': completing patching transition +transition: '$MOD_LIVEPATCH': starting patching transition +transition: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH': patching complete +transition: '$MOD_LIVEPATCH': patching complete % insmod test_modules/$MOD_LIVEPATCH2.ko replace=1 livepatch: enabling patch '$MOD_LIVEPATCH2' -livepatch: '$MOD_LIVEPATCH2': initializing patching transition +transition: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': starting patching transition -livepatch: '$MOD_LIVEPATCH2': completing patching transition +transition: '$MOD_LIVEPATCH2': starting patching transition +transition: '$MOD_LIVEPATCH2': completing patching transition $MOD_LIVEPATCH2: post_patch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': patching complete +transition: '$MOD_LIVEPATCH2': patching complete % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled -livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition +transition: '$MOD_LIVEPATCH2': initializing unpatching transition $MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': starting unpatching transition -livepatch: '$MOD_LIVEPATCH2': completing unpatching transition +transition: '$MOD_LIVEPATCH2': starting unpatching transition +transition: '$MOD_LIVEPATCH2': completing unpatching transition $MOD_LIVEPATCH2: post_unpatch_callback: vmlinux -livepatch: '$MOD_LIVEPATCH2': unpatching complete +transition: '$MOD_LIVEPATCH2': unpatching complete % rmmod $MOD_LIVEPATCH2 % rmmod $MOD_LIVEPATCH" -- 2.39.2

1 year

2
6
0 0

[PATCH v1] selftests: mm: Fix conversion specifiers in transact_test()

by guanjing

Lots of incorrect conversion specifiers. Fix them. Fixes: 46fd75d4a3c9 ("selftests: mm: add pagemap ioctl tests") Signed-off-by: guanjing <guanjing(a)cmss.chinamobile.com> --- tools/testing/selftests/mm/pagemap_ioctl.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index bcc73b4e805c..fdafce0654e9 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1405,9 +1405,9 @@ static void transact_test(int page_size) memset(mem, 0, 0x1000 * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count > 0, "%s count %d\n", __func__, count); + ksft_test_result(count > 0, "%s count %u\n", __func__, count); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count == 0, "%s count %d\n", __func__, count); + ksft_test_result(count == 0, "%s count %u\n", __func__, count); finish = 0; for (i = 0; i < nthreads; ++i) @@ -1429,7 +1429,7 @@ static void transact_test(int page_size) ksft_exit_fail_msg("pthread_barrier_wait\n"); if (count > nthreads * access_per_thread) - ksft_exit_fail_msg("Too big count %d expected %d, iter %d\n", + ksft_exit_fail_msg("Too big count %u expected %u, iter %u\n", count, nthreads * access_per_thread, i); c = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); @@ -1454,7 +1454,7 @@ static void transact_test(int page_size) * access and application gets page fault again for the same write. */ if (count < nthreads * access_per_thread) { - ksft_test_result_fail("Lost update, iter %d, %d vs %d.\n", i, count, + ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count, nthreads * access_per_thread); return; } @@ -1467,7 +1467,7 @@ static void transact_test(int page_size) finish = 1; pthread_barrier_wait(&end_barrier); - ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %d.\n", __func__, + ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %u.\n", __func__, extra_pages, 100.0 * extra_pages / (iter_count * nthreads * access_per_thread), extra_thread_faults); -- 2.33.0

1 year

2
2
0 0

[PATCH v2] selftests/lam: Test get_user() LAM pointer handling

by Maciej Wieczor-Retman

Recent change in how get_user() handles pointers [1] has a specific case for LAM. It assigns a different bitmask that's later used to check whether a pointer comes from userland in get_user(). While currently commented out (until LASS [2] is merged into the kernel) it's worth making changes to the LAM selftest ahead of time. Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses get_user() in its implementation. Execute the syscall with differently tagged pointers to verify that valid user pointers are passing through and invalid kernel/non-canonical pointers are not. Code was tested on a Sierra Forest Xeon machine that's LAM capable. The test was ran without issues with both the LAM lines from [1] untouched and commented out. The test was also ran without issues with LAM_SUP both enabled and disabled. 4/5 level pagetables code paths were also successfully tested in Simics on a 5-level capable machine. [1] https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundati… [2] https://lore.kernel.org/all/20240710160655.3402786-1-alexander.shishkin@lin… Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> --- Changelog v2: - Use mmap with HIGH_ADDR to check if we're in 5 or 4 level pagetables. tools/testing/selftests/x86/lam.c | 89 +++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..5818c075e1cd 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -4,6 +4,7 @@ #include <stdlib.h> #include <string.h> #include <sys/syscall.h> +#include <sys/ioctl.h> #include <time.h> #include <signal.h> #include <setjmp.h> @@ -43,7 +44,15 @@ #define FUNC_INHERITE 0x20 #define FUNC_PASID 0x40 +/* get_user() pointer test cases */ +#define GET_USER_USER 0 +#define GET_USER_KERNEL_TOP 1 +#define GET_USER_KERNEL_BOT 2 +#define GET_USER_KERNEL 3 + #define TEST_MASK 0x7f +#define L5_SIGN_EXT_MASK (0xFFUL << 56) +#define L4_SIGN_EXT_MASK (0x1FFFFUL << 47) #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) @@ -370,6 +379,59 @@ static int handle_syscall(struct testcases *test) return ret; } +static int get_user_syscall(struct testcases *test) +{ + int ptr_value = 0; + int ret = 0; + int fd; + void *p, *ptr = &ptr_value; + + p = mmap((void *)HIGH_ADDR, 1, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + + uint64_t bitmask = (p == MAP_FAILED) ? L4_SIGN_EXT_MASK : + L5_SIGN_EXT_MASK; + + munmap(p, 1); + + if (test->lam != 0) + if (set_lam(test->lam) != 0) + return 2; + + fd = memfd_create("lam_ioctl", 0); + if (fd == -1) + exit(EXIT_FAILURE); + + switch (test->later) { + case GET_USER_USER: + /* Control group - properly tagger user pointer */ + ptr = (void *)set_metadata((uint64_t)ptr, test->lam); + break; + case GET_USER_KERNEL_TOP: + /* Kernel address with top bit cleared */ + bitmask &= (bitmask >> 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL_BOT: + /* Kernel address with bottom sign-extension bit cleared */ + bitmask &= (bitmask << 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL: + /* Try to pass a kernel address */ + ptr = (void *)((uint64_t)ptr | bitmask); + break; + default: + printf("Invalid test case value passed!\n"); + break; + } + + if (ioctl(fd, FIOASYNC, ptr) != 0) + ret = 1; + + return ret; +} + int sys_uring_setup(unsigned int entries, struct io_uring_params *p) { return (int)syscall(__NR_io_uring_setup, entries, p); @@ -883,6 +945,33 @@ static struct testcases syscall_cases[] = { .test_func = handle_syscall, .msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", }, + { + .later = GET_USER_USER, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n", + }, + { + .later = GET_USER_KERNEL_TOP, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n", + }, + { + .later = GET_USER_KERNEL_BOT, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n", + }, + { + .later = GET_USER_KERNEL, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n", + }, }; static struct testcases mmap_cases[] = { -- 2.46.2

1 year

1
0
0 0

📈 Boost Your Rankings in Just 30 Days with Our One-Time SEO Plan!

by SEO MAX

Hi there, That’s right! With our one-time, one-month SEO plan , we’re ready to take your website’s rankings to the next level. Our team will implement proven strategies to optimize your site and secure quality backlinks, all designed to increase your visibility and drive results. Here’s what you’ll get: Full transparency on our work and approach. Comprehensive reports delivered within 30 days. Ready to see the difference? Try us today: https://www.1seo-max.com/get-started/ (https://www.1seo-max.com/get-started/) Or chat with us on Whatsapp: https://www.1seo-max.com/whatsapp-with-us/ (https://www.1seo-max.com/whatsapp-with-us/) Cheers, Mike Arnold Unsubscribe (https://clicks.1seo-max.com/?na=u&nk=1182396-88a37ab464&nek=24-) | Manage your subscription (https://clicks.1seo-max.com/?na=p&nk=1182396-88a37ab464&nek=24-) | View online (https://clicks.1seo-max.com/?na=v&nk=1182396-88a37ab464&id=24) whatsapp

1 year

1
0
0 0

[PATCH net-next] selftests: net/psock_lib: Handle EINTR and EAGAIN

by Leo Stone

Make pair_udp_send_char handle EAGAIN, EINTR, and partial reads or writes. Signed-off-by: Leo Stone <leocstone(a)gmail.com> --- tools/testing/selftests/net/psock_lib.h | 39 +++++++++++++++++++------ 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index 6e4fef560873..e28bff95c8e2 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -13,6 +13,7 @@ #include <string.h> #include <arpa/inet.h> #include <unistd.h> +#include <stdbool.h> #include "kselftest.h" @@ -110,21 +111,41 @@ static __maybe_unused void pair_udp_open(int fds[], uint16_t port) } } +static void read_write_checked(int fd, char *buf, size_t sz, bool is_write) +{ + int bytes_processed = 0; + int ret; + + do { + if (is_write) + ret = write(fd, buf + bytes_processed, + sz - bytes_processed); + else + ret = read(fd, buf + bytes_processed, + sz - bytes_processed); + if (ret == -1) { + if (errno == EAGAIN || errno == EINTR) { + continue; + } else { + fprintf(stderr, "ERROR: %s failed, bytes left=%lu\n", + is_write ? "send" : "recv", + sz - bytes_processed); + exit(1); + } + } + bytes_processed += ret; + } while (bytes_processed < sz); +} + static __maybe_unused void pair_udp_send_char(int fds[], int num, char payload) { char buf[DATA_LEN], rbuf[DATA_LEN]; memset(buf, payload, sizeof(buf)); while (num--) { - /* Should really handle EINTR and EAGAIN */ - if (write(fds[0], buf, sizeof(buf)) != sizeof(buf)) { - fprintf(stderr, "ERROR: send failed left=%d\n", num); - exit(1); - } - if (read(fds[1], rbuf, sizeof(rbuf)) != sizeof(rbuf)) { - fprintf(stderr, "ERROR: recv failed left=%d\n", num); - exit(1); - } + read_write_checked(fds[0], buf, sizeof(buf), true); + read_write_checked(fds[1], rbuf, sizeof(rbuf), false); + if (memcmp(buf, rbuf, sizeof(buf))) { fprintf(stderr, "ERROR: data failed left=%d\n", num); exit(1); -- 2.39.5

1 year

2
2
0 0

[PATCH] kunit: tool: add ability to parse test metadata

by Rae Moar

Add ability for kunit parser to parse test metadata introduced in KTAPv2. Example of test metadata: KTAP version 2 #:ktap_test: test_name_example #:ktap_speed: slow #:ktap_test_file: /sys/kernel/... 1..1 ok 1 test Also add tests for this feature. Note this patch would no longer allow the case where the main test is missing a test plan and the subtest does not use a KTAP version line in the header. However, this is also not an accepted KTAP format. Example: KTAP version 2 // missing test plan // missing KTAP version line # Subtest: test_suite 1..1 ok 1 test ok 1 test_suite Signed-off-by: Rae Moar <rmoar(a)google.com> --- lib/kunit/attributes.c | 23 ++++-- lib/kunit/debugfs.c | 2 +- lib/kunit/test.c | 9 +-- tools/testing/kunit/kunit_parser.py | 79 +++++++++++++------ tools/testing/kunit/kunit_tool_test.py | 12 ++- .../test_is_test_passed-missing_plan.log | 2 + .../kunit/test_data/test_parse_attributes.log | 6 +- .../kunit/test_data/test_parse_metadata.log | 11 +++ 8 files changed, 106 insertions(+), 38 deletions(-) create mode 100644 tools/testing/kunit/test_data/test_parse_metadata.log diff --git a/lib/kunit/attributes.c b/lib/kunit/attributes.c index 2cf04cc09372..85db4555d332 100644 --- a/lib/kunit/attributes.c +++ b/lib/kunit/attributes.c @@ -286,11 +286,17 @@ void kunit_print_attr(void *test_or_suite, bool is_test, unsigned int test_level { int i; bool to_free = false; + bool printed = false; void *attr; const char *attr_name, *attr_str; struct kunit_suite *suite = is_test ? NULL : test_or_suite; struct kunit_case *test = is_test ? test_or_suite : NULL; + if (suite) { + kunit_log(KERN_INFO, suite, "%*s#:ktap_test: %s", + KUNIT_INDENT_LEN * test_level, "", suite->name); + } + for (i = 0; i < ARRAY_SIZE(kunit_attr_list); i++) { if (kunit_attr_list[i].print == PRINT_NEVER || (test && kunit_attr_list[i].print == PRINT_SUITE)) @@ -300,12 +306,19 @@ void kunit_print_attr(void *test_or_suite, bool is_test, unsigned int test_level attr_name = kunit_attr_list[i].name; attr_str = kunit_attr_list[i].to_string(attr, &to_free); if (test) { - kunit_log(KERN_INFO, test, "%*s# %s.%s: %s", - KUNIT_INDENT_LEN * test_level, "", test->name, - attr_name, attr_str); + if (!printed) { + kunit_log(KERN_INFO, test, "%*s#:ktap_test: %s", + KUNIT_INDENT_LEN * test_level, "", + test->name); + printed = true; + } + kunit_log(KERN_INFO, test, "%*s#:ktap_%s: %s", + KUNIT_INDENT_LEN * test_level, "", + attr_name, attr_str); } else { - kunit_log(KERN_INFO, suite, "%*s# %s: %s", - KUNIT_INDENT_LEN * test_level, "", attr_name, attr_str); + kunit_log(KERN_INFO, suite, "%*s#:ktap_%s: %s", + KUNIT_INDENT_LEN * test_level, "", + attr_name, attr_str); } /* Free to_string of attribute if needed */ diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index af71911f4a07..035cdae9d8b8 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -78,7 +78,7 @@ static int debugfs_print_results(struct seq_file *seq, void *v) /* Print suite header because it is not stored in the test logs. */ seq_puts(seq, KUNIT_SUBTEST_INDENT "KTAP version 1\n"); - seq_printf(seq, KUNIT_SUBTEST_INDENT "# Subtest: %s\n", suite->name); + seq_printf(seq, KUNIT_SUBTEST_INDENT "#:ktap_test: %s\n", suite->name); seq_printf(seq, KUNIT_SUBTEST_INDENT "1..%zd\n", kunit_suite_num_test_cases(suite)); kunit_suite_for_each_test_case(suite, test_case) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 089c832e3cdb..4fcc39e87983 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -158,8 +158,6 @@ static void kunit_print_suite_start(struct kunit_suite *suite) * representation. */ pr_info(KUNIT_SUBTEST_INDENT "KTAP version 1\n"); - pr_info(KUNIT_SUBTEST_INDENT "# Subtest: %s\n", - suite->name); kunit_print_attr((void *)suite, false, KUNIT_LEVEL_CASE); pr_info(KUNIT_SUBTEST_INDENT "1..%zd\n", kunit_suite_num_test_cases(suite)); @@ -627,9 +625,11 @@ int kunit_run_tests(struct kunit_suite *suite) if (test_case->status == KUNIT_SKIPPED) { /* Test marked as skip */ test.status = KUNIT_SKIPPED; + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); kunit_update_stats(&param_stats, test.status); } else if (!test_case->generate_params) { /* Non-parameterised test. */ + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); test_case->status = KUNIT_SKIPPED; kunit_run_case_catch_errors(suite, test_case, &test); kunit_update_stats(&param_stats, test.status); @@ -641,7 +641,8 @@ int kunit_run_tests(struct kunit_suite *suite) kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT "KTAP version 1\n"); kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT - "# Subtest: %s", test_case->name); + "#:ktap_test: %s", test_case->name); + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); while (test.param_value) { kunit_run_case_catch_errors(suite, test_case, &test); @@ -669,8 +670,6 @@ int kunit_run_tests(struct kunit_suite *suite) } } - kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); - kunit_print_test_stats(&test, param_stats); kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status, diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 29fc27e8949b..52dcbad52ade 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -247,7 +247,7 @@ def extract_tap_lines(kernel_output: Iterable[str]) -> LineStream: yield line_num, line return LineStream(lines=isolate_ktap_output(kernel_output)) -KTAP_VERSIONS = [1] +KTAP_VERSIONS = [1, 2] TAP_VERSIONS = [13, 14] def check_version(version_num: int, accepted_versions: List[int], @@ -324,6 +324,39 @@ def parse_test_header(lines: LineStream, test: Test) -> bool: lines.pop() return True +TEST_METADATA_HEADER = re.compile(r'^\s*#:ktap_test: (.*)$') +TEST_METADATA = re.compile(r'^\s*#:(ktap_.*): (.*)$') + +def parse_test_metadata(lines: LineStream, test: Test) -> bool: + """ + Parses test metadata and stores test information in test object. + Returns False if fails to parse test metadata lines + + Accepted format: + - '# [metadata_category]: [metadata]' + + Recognized metadata categories: + - 'ktap_test' to indicate test name + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if successfully parsed test metadata + """ + match = TEST_METADATA_HEADER.match(lines.peek()) + if not match: + return False + test.name = match.group(1) + test.log.append(lines.pop()) + non_metadata_lines = [TEST_PLAN, TEST_RESULT, KTAP_START] + while lines and not any(re.match(lines.peek()) + for re in non_metadata_lines): + # Add checks for metadata cateories here: Attributes, Files, Other... + test.log.append(lines.pop()) + return True + TEST_PLAN = re.compile(r'^\s*1\.\.([0-9]+)') def parse_test_plan(lines: LineStream, test: Test) -> bool: @@ -442,6 +475,7 @@ def parse_diagnostic(lines: LineStream) -> List[str]: Line formats that are not parsed: - '# Subtest: [test name]' + - '#:ktap_test: [test name]' - '[ok|not ok] [test number] [-] [test name] [optional skip directive]' - 'KTAP version [version number]' @@ -453,7 +487,8 @@ def parse_diagnostic(lines: LineStream) -> List[str]: Log of diagnostic lines """ log = [] # type: List[str] - non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START, TEST_PLAN] + non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START, + TEST_PLAN, TEST_METADATA_HEADER] while lines and not any(re.match(lines.peek()) for re in non_diagnostic_lines): log.append(lines.pop()) @@ -504,7 +539,7 @@ def print_test_header(test: Test, printer: Printer) -> None: message = test.name if message != "": # Add a leading space before the subtest counts only if a test name - # is provided using a "# Subtest" header line. + # is provided using a "#:ktap_test" or "# Subtest" header line. message += " " if test.expected_count: if test.expected_count == 1: @@ -702,6 +737,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: Example: KTAP version 1 + [test metadata] 1..4 [subtests] @@ -709,10 +745,11 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: "# Subtest" header line) Example (preferred format with both KTAP version line and - "# Subtest" line): + "#:ktap_test" line): KTAP version 1 - # Subtest: name + #:ktap_test: name + [test metadata] 1..3 [subtests] ok 1 name @@ -727,6 +764,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: Example (only KTAP version line, compliant with KTAP v1 spec): KTAP version 1 + [test metadata] 1..3 [subtests] ok 1 name @@ -755,26 +793,23 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: err_log = parse_diagnostic(lines) test.log.extend(err_log) - if not is_subtest: - # If parsing the main/top-level test, parse KTAP version line and - # test plan - test.name = "main" - ktap_line = parse_ktap_header(lines, test, printer) - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) - parent_test = True - else: - # If not the main test, attempt to parse a test header containing - # the KTAP version line and/or subtest header line - ktap_line = parse_ktap_header(lines, test, printer) - subtest_line = parse_test_header(lines, test) + # If parsing the main/top-level test, parse KTAP version line, any + # test metadata, and test plan + ktap_line = parse_ktap_header(lines, test, printer) + subtest_line = parse_test_header(lines, test) + parse_test_metadata(lines, test) + parse_test_plan(lines, test) + + # Determine if the test is a parent test + if is_subtest: parent_test = (ktap_line or subtest_line) if parent_test: - # If KTAP version line and/or subtest header is found, attempt - # to parse test plan and print test header - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) print_test_header(test, printer) + else: + parent_test = True + if test.name == "": + test.name = "main" + expected_count = test.expected_count subtests = [] test_num = 1 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0bcb0cc002f8..6ff422399130 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -345,8 +345,8 @@ class KUnitParserTest(unittest.TestCase): self.print_mock.assert_any_call(StrContains('suite (1 subtest)')) # Ensure attributes in correct test log - self.assertContains('# module: example', result.subtests[0].log) - self.assertContains('# test.speed: slow', result.subtests[0].subtests[0].log) + self.assertContains('#:ktap_module: example', result.subtests[0].log) + self.assertContains('#:ktap_speed: slow', result.subtests[0].subtests[0].log) def test_show_test_output_on_failure(self): output = """ @@ -363,6 +363,14 @@ class KUnitParserTest(unittest.TestCase): self.print_mock.assert_any_call(StrContains(' Indented more.')) self.noPrintCallContains('not ok 1 test1') + def test_metadata(self): + name_log = test_data_path('test_parse_metadata.log') + with open(name_log) as file: + result = kunit_parser.parse_run_tests(file.readlines(), stdout) + self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) + self.assertEqual("main_test", result.name) + self.assertContains("#:ktap_speed: slow", result.subtests[0].log) + def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream: return kunit_parser.LineStream(enumerate(strs, start=1)) diff --git a/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log b/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log index 5cd17b7f818a..1e952b0430e1 100644 --- a/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log +++ b/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log @@ -1,4 +1,5 @@ KTAP version 1 + KTAP version 1 # Subtest: sysctl_test # sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed ok 1 - sysctl_test_dointvec_null_tbl_data @@ -18,6 +19,7 @@ KTAP version 1 ok 8 - sysctl_test_dointvec_single_greater_int_max kunit sysctl_test: all tests passed ok 1 - sysctl_test + KTAP version 1 # Subtest: example 1..2 init_suite diff --git a/tools/testing/kunit/test_data/test_parse_attributes.log b/tools/testing/kunit/test_data/test_parse_attributes.log index 1a13c371fe9d..d7961422c66f 100644 --- a/tools/testing/kunit/test_data/test_parse_attributes.log +++ b/tools/testing/kunit/test_data/test_parse_attributes.log @@ -1,9 +1,9 @@ KTAP version 1 1..1 KTAP version 1 - # Subtest: suite - # module: example + #:ktap_test: suite + #:ktap_module: example 1..1 - # test.speed: slow + #:ktap_speed: slow ok 1 test ok 1 suite \ No newline at end of file diff --git a/tools/testing/kunit/test_data/test_parse_metadata.log b/tools/testing/kunit/test_data/test_parse_metadata.log new file mode 100644 index 000000000000..2094867110e5 --- /dev/null +++ b/tools/testing/kunit/test_data/test_parse_metadata.log @@ -0,0 +1,11 @@ +KTAP version 2 +#:ktap_test: main_test +#:ktap_module: example +1..2 + KTAP version 2 + #:ktap_test: test_1 + #:ktap_speed: slow + 1..1 + ok 1 subtest_1 +ok 1 test_1 +ok 2 test_2 \ No newline at end of file base-commit: 62adcae479fe5bc04fa3b6c3f93bd340441f8b25 -- 2.47.0.338.g60cca15819-goog

1 year

1
0
0 0

[GIT PULL] Kselftest update for Linux 6.13-rc1

by Shuah Khan

Hi Linus, Please pull the following kselftest fixes update for Linux 6.13-rc1. kselftest update for Linux 6.13-rc1 -- timers test - removes duplicates defines -- timers test - fixes to improve error reporting -- rtc test - adds check rtc alarm status to alarm test -- resctrl test - adds array overrun checks during iMC config parsing code -- resctrl test - adds array overflow checks when reading strings -- resctrl test - fixes and reorganizing code Looks like I forgot to mention signal test changes in my tag message. :( diff is attached. Tests passed on my kselftest next branch: - Individual test runs of signal, timers, rtc, and resctrl thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 8e929cb546ee42c9a61d24fae60605e9e3192354: Linux 6.12-rc3 (2024-10-13 14:33:32 -0700) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-next-6.13-rc1 for you to fetch changes up to a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38: selftests/resctrl: Replace magic constants used as array size (2024-11-04 17:02:03 -0700) ---------------------------------------------------------------- linux_kselftest-next-6.13-rc1 kselftest update for Linux 6.13-rc1 -- timers test - removes duplicates defines -- timers test - fixes to improve error reporting -- rtc test - adds check rtc alarm status to alarm test -- resctrl test - adds array overrun checks during iMC config parsing code -- resctrl test - adds array overflow checks when reading strings -- resctrl test - fixes and reorganizing code ---------------------------------------------------------------- Chen Ni (1): selftests: timers: Remove unneeded semicolon Dev Jain (2): selftests: Rename sigaltstack to generic signal selftests: Add a test mangling with uc_sigmask Gianfranco Trad (1): selftests: timers: improve timer_create failure message Joseph Jang (1): selftest: rtc: Add to check rtc alarm status for alarm related test Nícolas F. R. A. Prado (1): docs: dev-tools: Add documentation for the device focused kselftests Reinette Chatre (15): selftests/resctrl: Make functions only used in same file static selftests/resctrl: Print accurate buffer size as part of MBM results selftests/resctrl: Fix memory overflow due to unhandled wraparound selftests/resctrl: Protect against array overrun during iMC config parsing selftests/resctrl: Protect against array overflow when reading strings selftests/resctrl: Make wraparound handling obvious selftests/resctrl: Remove "once" parameter required to be false selftests/resctrl: Only support measured read operation selftests/resctrl: Remove unused measurement code selftests/resctrl: Make benchmark parameter passing robust selftests/resctrl: Ensure measurements skip initialization of default benchmark selftests/resctrl: Use cache size to determine "fill_buf" buffer size selftests/resctrl: Do not compare performance counters and resctrl at low bandwidth selftests/resctrl: Keep results from first test run selftests/resctrl: Replace magic constants used as array size Shuah Khan (2): selftests: timers: Remove local NSEC_PER_SEC and USEC_PER_SEC defines selftests:timers: remove local CLOCKID defines Documentation/dev-tools/kselftest.rst | 9 + Documentation/dev-tools/testing-devices.rst | 47 +++ tools/testing/selftests/Makefile | 2 +- tools/testing/selftests/resctrl/cmt_test.c | 37 +- tools/testing/selftests/resctrl/fill_buf.c | 45 +-- tools/testing/selftests/resctrl/mba_test.c | 54 ++- tools/testing/selftests/resctrl/mbm_test.c | 37 +- tools/testing/selftests/resctrl/resctrl.h | 79 +++- tools/testing/selftests/resctrl/resctrl_tests.c | 95 ++++- tools/testing/selftests/resctrl/resctrl_val.c | 447 ++++++--------------- tools/testing/selftests/resctrl/resctrlfs.c | 19 +- tools/testing/selftests/rtc/Makefile | 2 +- tools/testing/selftests/rtc/rtctest.c | 64 +++ .../selftests/{sigaltstack => signal}/.gitignore | 1 + .../selftests/{sigaltstack => signal}/Makefile | 3 +- .../current_stack_pointer.h | 0 tools/testing/selftests/signal/mangle_uc_sigmask.c | 184 +++++++++ .../selftests/{sigaltstack => signal}/sas.c | 0 tools/testing/selftests/timers/Makefile | 2 +- tools/testing/selftests/timers/adjtick.c | 6 +- .../testing/selftests/timers/alarmtimer-suspend.c | 22 +- .../testing/selftests/timers/inconsistency-check.c | 21 +- tools/testing/selftests/timers/leap-a-day.c | 2 +- tools/testing/selftests/timers/mqueue-lat.c | 2 +- tools/testing/selftests/timers/nanosleep.c | 21 +- tools/testing/selftests/timers/nsleep-lat.c | 22 +- tools/testing/selftests/timers/posix_timers.c | 15 +- tools/testing/selftests/timers/raw_skew.c | 4 +- tools/testing/selftests/timers/set-2038.c | 3 +- tools/testing/selftests/timers/set-timer-lat.c | 21 +- tools/testing/selftests/timers/valid-adjtimex.c | 4 +- 31 files changed, 701 insertions(+), 569 deletions(-) create mode 100644 Documentation/dev-tools/testing-devices.rst rename tools/testing/selftests/{sigaltstack => signal}/.gitignore (70%) rename tools/testing/selftests/{sigaltstack => signal}/Makefile (56%) rename tools/testing/selftests/{sigaltstack => signal}/current_stack_pointer.h (100%) create mode 100644 tools/testing/selftests/signal/mangle_uc_sigmask.c rename tools/testing/selftests/{sigaltstack => signal}/sas.c (100%) ----------------------------------------------------------------

1 year

2
1
0 0

[RFCv1 0/6] Page Detective

by Pasha Tatashin

Page Detective is a new kernel debugging tool that provides detailed information about the usage and mapping of physical memory pages. It is often known that a particular page is corrupted, but it is hard to extract more information about such a page from live system. Examples are: - Checksum failure during live migration - Filesystem journal failure - dump_page warnings on the console log - Unexcpected segfaults Page Detective helps to extract more information from the kernel, so it can be used by developers to root cause the associated problem. It operates through the Linux debugfs interface, with two files: "virt" and "phys". The "virt" file takes a virtual address and PID and outputs information about the corresponding page. The "phys" file takes a physical address and outputs information about that page. The output is presented via kernel log messages (can be accessed with dmesg), and includes information such as the page's reference count, mapping, flags, and memory cgroup. It also shows whether the page is mapped in the kernel page table, and if so, how many times. Pasha Tatashin (6): mm: Make get_vma_name() function public pagewalk: Add a page table walker for init_mm page table mm: Add a dump_page variant that accept log level argument misc/page_detective: Introduce Page Detective misc/page_detective: enable loadable module selftests/page_detective: Introduce self tests for Page Detective Documentation/misc-devices/index.rst | 1 + Documentation/misc-devices/page_detective.rst | 78 ++ MAINTAINERS | 8 + drivers/misc/Kconfig | 11 + drivers/misc/Makefile | 1 + drivers/misc/page_detective.c | 808 ++++++++++++++++++ fs/inode.c | 18 +- fs/kernfs/dir.c | 1 + fs/proc/task_mmu.c | 61 -- include/linux/fs.h | 5 +- include/linux/mmdebug.h | 1 + include/linux/pagewalk.h | 2 + kernel/pid.c | 1 + mm/debug.c | 53 +- mm/memcontrol.c | 1 + mm/oom_kill.c | 1 + mm/pagewalk.c | 32 + mm/vma.c | 60 ++ tools/testing/selftests/Makefile | 1 + .../selftests/page_detective/.gitignore | 1 + .../testing/selftests/page_detective/Makefile | 7 + tools/testing/selftests/page_detective/config | 4 + .../page_detective/page_detective_test.c | 727 ++++++++++++++++ 23 files changed, 1787 insertions(+), 96 deletions(-) create mode 100644 Documentation/misc-devices/page_detective.rst create mode 100644 drivers/misc/page_detective.c create mode 100644 tools/testing/selftests/page_detective/.gitignore create mode 100644 tools/testing/selftests/page_detective/Makefile create mode 100644 tools/testing/selftests/page_detective/config create mode 100644 tools/testing/selftests/page_detective/page_detective_test.c -- 2.47.0.338.g60cca15819-goog

1 year

11
42
0 0

KUnit expectations in atomic context

by Brendan Jackman

Hi all, Another rather vague question from me - does anyone know any reasons why we couldn't support KUNIT_EXPECT in atomic contexts? For Address Space Isolation we have some tests that want to disable preemption. I guess this is not a totally insane thing to want to do - am I missing anything there? You can see some examples here: https://github.com/googleprodkernel/linux-kvm/blob/asi-lpc-24/arch/x86/mm/a… (Actually, looks like in that code we just started doing KUNIT_EXPECT in preempt-disabled regions anyway, and I never suffered any consequences until recently. Probably we just never had those assertions fail under DEBUG_ATOMIC_SLEEP). From a very quick look, it seems like the only reason you can't KUNIT_EXPECT from atomic right now is the GFP_KERNEL allocations. So... what if we just made them GFP_ATOMIC? In general I think that's a pretty ropey approach, but maybe fine in the context of unit tests? Or, we could have variants of the assertions, or a test attribute, to just use GFP_ATOMIC in the cases where it's needed. Is there anything else missing that would need to be done? Alternatively, we could expose the whole context concern to the user in such a way that KUNIT_ASSERT can be used too, something like: struct kunit_defer defer = KUNIT_INIT_DEFER(test); preempt_disable(); KUNIT_EXPECT_DEFERRED_TRUE(&defer, ...); KUNIT_ASSERT_DEFERRED_EQ(&defer, ...); preempt_enable(); // Prints failures from above, aborts if the ASSERT failed: kunit_defer_finish(&defer); I hope that wouldn't be necessary though, it seems like a lot of API surface.

1 year

1
0
0 0

[PATCH] selftests/mount_setattr: Fix failures on 64K PAGE_SIZE kernels

by Michael Ellerman

Currently the mount_setattr_test fails on machines with a 64K PAGE_SIZE, with errors such as: # RUN mount_setattr_idmapped.invalid_fd_negative ... mkfs.ext4: No space left on device while writing out and closing file system # mount_setattr_test.c:1055:invalid_fd_negative:Expected system("mkfs.ext4 -q /mnt/C/ext4.img") (256) == 0 (0) # invalid_fd_negative: Test terminated by assertion # FAIL mount_setattr_idmapped.invalid_fd_negative not ok 12 mount_setattr_idmapped.invalid_fd_negative The code creates a 100,000 byte tmpfs: ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, "size=100000,mode=700"), 0); And then a little later creates a 2MB ext4 filesystem in that tmpfs: ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0); ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0); At first glance it seems like that should never work, after all 2MB is larger than 100,000 bytes. However the filesystem image doesn't actually occupy 2MB on "disk" (actually RAM, due to tmpfs). On 4K kernels the ext4.img uses ~84KB of actual space (according to du), which just fits. However on 64K PAGE_SIZE kernels the ext4.img takes at least 256KB, which is too large to fit in the tmpfs, hence the errors. It seems fraught to rely on the ext4.img taking less space on disk than the allocated size, so instead create the tmpfs with a size of 2MB. With that all 21 tests pass on 64K PAGE_SIZE kernels. Fixes: 01eadc8dd96d ("tests: add mount_setattr() selftests") Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 68801e1a9ec2..70f65eb320a7 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1026,7 +1026,7 @@ FIXTURE_SETUP(mount_setattr_idmapped) "size=100000,mode=700"), 0); ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, - "size=100000,mode=700"), 0); + "size=2m,mode=700"), 0); ASSERT_EQ(mkdir("/mnt/A", 0777), 0); -- 2.47.0

1 year

3
2
0 0

[GIT PULL] KUnit update for Linux 6.13-rc1

by Shuah Khan

Hi Linus, Please pull the following kunit update for Linux 6.13-rc1. kunit update for Linux 6.13-rc1 -- fixes user-after-free (UAF) bug in kunit_init_suite() -- adds option to kunit tool to print just the summary of test results -- adds option to kunit tool to print just the failed test results -- fixes kunit_zalloc_skb() to use user passed in gfp value instead of hardcoding GFP_KERNEL -- fixes kunit_zalloc_skb() kernel doc to include allocation flags variable diff is attached. Tests passed on my kunit repo: - Build make allmodconfig ./tools/testing/kunit/kunit.py run ./tools/testing/kunit/kunit.py run --alltests ./tools/testing/kunit/kunit.py run --arch x86_64 ./tools/testing/kunit/kunit.py run --alltests --arch x86_64 thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 2d5404caa8c7bb5c4e0435f94b28834ae5456623: Linux 6.12-rc7 (2024-11-10 14:19:35 -0800) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-kunit-6.13-rc1 for you to fetch changes up to 67b6d342fb6d5abfbeb71e0f23141b9b96cf7bb1: kunit: tool: print failed tests only (2024-11-14 09:38:19 -0700) ---------------------------------------------------------------- linux_kselftest-kunit-6.13-rc1 kunit update for Linux 6.13-rc1 -- fixes user-after-free (UAF) bug in kunit_init_suite() -- adds option to kunit tool to print just the summary of test results -- adds option to kunit tool to print just the failed test results -- fixes kunit_zalloc_skb() to use user passed in gfp value instead of hardcoding GFP_KERNEL -- fixes kunit_zalloc_skb() kernel doc to include allocation flags variable ---------------------------------------------------------------- Dan Carpenter (2): kunit: skb: use "gfp" variable instead of hardcoding GFP_KERNEL kunit: skb: add gfp to kernel doc for kunit_zalloc_skb() David Gow (1): kunit: tool: Only print the summary Jinjie Ruan (1): kunit: string-stream: Fix a UAF bug in kunit_init_suite() Rae Moar (1): kunit: tool: print failed tests only include/kunit/skbuff.h | 5 +- lib/kunit/string-stream.c | 1 + tools/testing/kunit/kunit.py | 28 ++++++- tools/testing/kunit/kunit_parser.py | 134 +++++++++++++++++++++------------ tools/testing/kunit/kunit_printer.py | 14 +++- tools/testing/kunit/kunit_tool_test.py | 55 +++++++------- 6 files changed, 151 insertions(+), 86 deletions(-) ----------------------------------------------------------------

1 year

2
3
0 0

[PATCHv2 net-next] selftests: wireguards: use nft by default

by Hangbin Liu

Use nft by default if it's supported, as nft is the replacement for iptables, which is used by default in some releases. Additionally, iptables is dropped in some releases. Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v2: use one nft table for testing (Phil Sutter) --- tools/testing/selftests/wireguard/netns.sh | 63 ++++++++++++++++++---- 1 file changed, 53 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..be4e3b13ed22 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -44,6 +44,7 @@ sleep() { read -t "$1" -N 1 || true; } waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } +use_nft() { nft --version &> /dev/null; } cleanup() { set +e @@ -75,6 +76,12 @@ pp ip netns add $netns1 pp ip netns add $netns2 ip0 link set up dev lo +if use_nft; then + n0 nft add table ip wgtest + n1 nft add table ip wgtest + n2 nft add table ip wgtest +fi + ip0 link add dev wg0 type wireguard ip0 link set wg0 netns $netns1 ip0 link add dev wg0 type wireguard @@ -196,13 +203,22 @@ ip1 link set wg0 mtu 1300 ip2 link set wg0 mtu 1300 n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 -n0 iptables -A INPUT -m length --length 1360 -j DROP +if use_nft; then + n0 nft add chain ip wgtest INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule ip wgtest INPUT meta length 1360 counter drop +else + n0 iptables -A INPUT -m length --length 1360 -j DROP +fi n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 n2 ping -c 1 -W 1 -s 1269 192.168.241.1 n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 -n0 iptables -F INPUT +if use_nft; then + n0 nft flush table ip wgtest +else + n0 iptables -F INPUT +fi ip1 link set wg0 mtu $orig_mtu ip2 link set wg0 mtu $orig_mtu @@ -334,7 +350,12 @@ waitiface $netns2 veths n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' -n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +if use_nft; then + n0 nft add chain ip wgtest POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n0 nft add rule ip wgtest POSTROUTING ip saddr 192.168.1.0/24 ip daddr 10.0.0.0/24 counter snat to 10.0.0.1 +else + n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +fi n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 n1 ping -W 1 -c 1 192.168.241.2 @@ -348,10 +369,19 @@ n1 wg set wg0 peer "$pub2" persistent-keepalive 0 # Test that sk_bound_dev_if works n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # What about when the mark changes and the packet must be rerouted? -n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft add chain ip wgtest OUTPUT { type route hook output priority mangle\; policy accept \; } + n1 nft add rule ip wgtest OUTPUT counter meta mark set 0x1 +else + n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +fi n1 ping -c 1 -W 1 192.168.241.2 # First the boring case n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case -n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft flush table ip wgtest +else + n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +fi # Test that onion routing works, even when it loops n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 @@ -385,16 +415,29 @@ n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 # Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. -n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 -n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +if use_nft; then + n2 nft add chain ip wgtest POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n2 nft add rule ip wgtest POSTROUTING ip saddr 10.0.0.0/24 ip daddr 192.168.241.0/24 counter snat to 192.168.241.2 + + n0 nft add chain ip wgtest INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule ip wgtest INPUT iifname "vethrs" ip saddr != 10.0.0.0/24 counter drop +else + n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 + n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +fi n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' ip0 -4 route add 192.168.241.1 via 10.0.0.100 n2 wg set wg0 peer "$pub1" remove [[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] -n0 iptables -t nat -F -n0 iptables -t filter -F -n2 iptables -t nat -F +if use_nft; then + n0 nft flush table ip wgtest + n2 nft flush table ip wgtest +else + n0 iptables -t nat -F + n0 iptables -t filter -F + n2 iptables -t nat -F +fi ip0 link del vethrc ip0 link del vethrs ip1 link del wg0 -- 2.39.5 (Apple Git-154)

1 year

3
4
0 0

[PATCH net-next v2] mm: page_frag: fix a compile error when kernel is not compiled

by Yunsheng Lin

page_frag test module is an out of tree module, but built using KDIR as the main kernel tree, the mm test suite is just getting skipped if newly added page_frag test module fails to compile due to kernel not yet compiled. Fix the above problem by ensuring both kernel is built first and a newer kernel which has page_frag_cache.h is used. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexanderduyck(a)fb.com> CC: Linux-MM <linux-mm(a)kvack.org> Fixes: 7fef0dec415c ("mm: page_frag: add a test module for page_frag") Fixes: 65941f10caf2 ("mm: move the page fragment allocator from page_alloc into its own file") Reported-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Tested-by: Mark Brown <broonie(a)kernel.org> --- V2: Repost by adding net-next ML. Note, page_frag test module is only in the net-next tree for now, so target the net-next tree. --- tools/testing/selftests/mm/Makefile | 18 ++++++++++++++++++ tools/testing/selftests/mm/page_frag/Makefile | 2 +- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index acec529baaca..04e04733fc8a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,7 +36,16 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +KDIR ?= /lib/modules/$(shell uname -r)/build +ifneq (,$(wildcard $(KDIR)/Module.symvers)) +ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) TEST_GEN_MODS_DIR := page_frag +else +PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel" +endif +else +PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first" +endif TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test @@ -214,3 +223,12 @@ warn_missing_liburing: echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif + +ifneq ($(PAGE_FRAG_WARNING),) +all: warn_missing_page_frag + +warn_missing_page_frag: + @echo ; \ + echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \ + echo +endif diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile index 58dda74d50a3..8c8bb39ffa28 100644 --- a/tools/testing/selftests/mm/page_frag/Makefile +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -1,5 +1,5 @@ PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) +KDIR ?= /lib/modules/$(shell uname -r)/build ifeq ($(V),1) Q = -- 2.33.0

1 year

3
2
0 0

[PATCH v2] net/unix: pass pidfd flags via SCM_PIDFD cmsg

by Stas Sergeev

Currently SCM_PIDFD cmsg cannot be sent via unix socket (returns -EINVAL) and SO_PASSPIDFD doesn't support flags. The created pidfd always has flags set to 0. This patch implements SCM_PIDFD cmsg in AF_UNIX socket, which can be used to send flags to SO_PASSPIDFD-enabled recipient. Self-test is added for the propagation of PIDFD_NONBLOCK flag. This is mainly needed for the future extensions, like eg this one: https://lore.kernel.org/lkml/8288a08e-448b-43c2-82dc-59f87d0d9072@yandex.ru… where it was suggested to try solving the supplementary groups problem with pidfd. Changes in v2: remove flags validation in scm_pidfd_recv(), as suggested by Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: Stas Sergeev <stsp2(a)yandex.ru> 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: Simon Horman <horms(a)kernel.org> CC: Shuah Khan <shuah(a)kernel.org> CC: Christian Brauner <brauner(a)kernel.org> CC: Jens Axboe <axboe(a)kernel.dk> CC: Willem de Bruijn <willemb(a)google.com> CC: Pavel Begunkov <asml.silence(a)gmail.com> CC: Gabriel Krisman Bertazi <krisman(a)suse.de> CC: Mina Almasry <almasrymina(a)google.com> CC: Oleg Nesterov <oleg(a)redhat.com> CC: Tycho Andersen <tandersen(a)netflix.com> CC: Al Viro <viro(a)zeniv.linux.org.uk> CC: Kuniyuki Iwashima <kuniyu(a)amazon.com> CC: Gou Hao <gouhao(a)uniontech.com> CC: Abhishek Chauhan <quic_abchauha(a)quicinc.com> CC: Michal Luczaj <mhal(a)rbox.co> CC: Kees Cook <kees(a)kernel.org> CC: Aleksa Sarai <cyphar(a)cyphar.com> CC: linux-kernel(a)vger.kernel.org CC: netdev(a)vger.kernel.org CC: linux-kselftest(a)vger.kernel.org --- include/linux/pidfs.h | 9 +++ include/linux/socket.h | 2 +- include/net/af_unix.h | 1 + include/net/scm.h | 3 +- kernel/pid.c | 6 +- net/core/scm.c | 14 ++++ net/core/sock.c | 1 + net/unix/af_unix.c | 3 + .../testing/selftests/net/af_unix/scm_pidfd.c | 70 +++++++++++++++++-- 9 files changed, 99 insertions(+), 10 deletions(-) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..c4c5c1a0c2ad 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,7 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +#include <uapi/linux/pidfd.h> + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +static inline int pidfd_validate_flags(unsigned int flags) +{ + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) + return -EINVAL; + return 0; +} + #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..ee27d391e5aa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -178,7 +178,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD 0x04 /* r: pidfd, w: pidfd_flags (int) */ struct ucred { __u32 pid; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 63129c79b8cb..4bc197548c2f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_skb_parms { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif + u32 pidfd_flags; u32 consumed; } __randomize_layout; diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..1326edcacacb 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -48,6 +48,7 @@ struct scm_cookie { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Passed security ID */ #endif + u32 pidfd_flags; }; void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); @@ -154,7 +155,7 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm if (!scm->pid) return; - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + pidfd = pidfd_prepare(scm->pid, scm->pidfd_flags, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..b1100ae8ea63 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -629,10 +629,12 @@ static int pidfd_create(struct pid *pid, unsigned int flags) SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; + int err; struct pid *p; - if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) - return -EINVAL; + err = pidfd_validate_flags(flags); + if (err) + return err; if (pid <= 0) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..3bcdecdacd7e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -23,6 +23,7 @@ #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> @@ -210,6 +211,19 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->creds.gid = gid; break; } + case SCM_PIDFD: + { + unsigned int flags; + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(flags))) + goto error; + memcpy(&flags, CMSG_DATA(cmsg), sizeof(flags)); + err = pidfd_validate_flags(flags); + if (err) + goto error; + p->pidfd_flags = flags; + break; + } default: goto error; } diff --git a/net/core/sock.c b/net/core/sock.c index 039be95c40cf..d1fce437c035 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2930,6 +2930,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: + case SCM_PIDFD: break; default: return -EINVAL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..8b19dfec0221 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1892,6 +1892,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; + UNIXCB(skb).pidfd_flags = scm->pidfd_flags; unix_get_secdata(scm, skb); if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -2486,6 +2487,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); if (!(flags & MSG_PEEK)) { @@ -2873,6 +2875,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); check_creds = true; } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..1e70ff253a1d 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -5,6 +5,7 @@ #include <stddef.h> #include <stdio.h> #include <stdlib.h> +#include <fcntl.h> #include <sys/socket.h> #include <linux/socket.h> #include <unistd.h> @@ -15,6 +16,11 @@ #include <sys/types.h> #include <sys/wait.h> +/* There are problems including linux/pidfd.h, so define. */ +#ifndef PIDFD_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#endif + #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -126,7 +132,7 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } -static int cmsg_check(int fd) +static int cmsg_check(int fd, unsigned int pidfd_flags) { struct msghdr msg = { 0 }; struct cmsghdr *cmsg; @@ -136,6 +142,7 @@ static int cmsg_check(int fd) char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; int *pidfd = NULL; + unsigned int flags; pid_t parent_pid; int err; @@ -197,6 +204,13 @@ static int cmsg_check(int fd) return 1; } + flags = fcntl(*pidfd, F_GETFL, 0); + flags &= ~O_ACCMODE; + if (flags != pidfd_flags) { + log_err("SCM_PIDFD flags mismatch: %x != %x", flags, pidfd_flags); + 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); @@ -227,30 +241,49 @@ FIXTURE_VARIANT(scm_pidfd) { int type; bool abstract; + unsigned int flags; }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) { .type = SOCK_STREAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) { .type = SOCK_STREAM, .abstract = 1, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) { .type = SOCK_DGRAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) { .type = SOCK_DGRAM, .abstract = 1, + .flags = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_nonblock) +{ + .type = SOCK_STREAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_nonblock) +{ + .type = SOCK_DGRAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, }; FIXTURE_SETUP(scm_pidfd) @@ -335,7 +368,7 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, close(self->startup_pipe[1]); - if (cmsg_check(cfd)) { + if (cmsg_check(cfd, variant->flags)) { log_err("cmsg_check failed"); child_die(); } @@ -375,6 +408,27 @@ TEST_F(scm_pidfd, test) int err; int pfd; int child_status = 0; + char iobuf; + unsigned int pidfd_flags; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec io = { + .iov_base = &iobuf, + .iov_len = sizeof(iobuf) + }; + union { + char buf[CMSG_SPACE(sizeof(pidfd_flags))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_PIDFD; + cmsg->cmsg_len = CMSG_LEN(sizeof(pidfd_flags)); self->server = socket(AF_UNIX, variant->type, 0); ASSERT_NE(-1, self->server); @@ -414,12 +468,16 @@ TEST_F(scm_pidfd, test) 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); + err = connect(pfd, + (struct sockaddr *)&self->client_addr->listen_addr, + self->client_addr->addrlen); ASSERT_NE(-1, err); } + iobuf = 'x'; + pidfd_flags = variant->flags; + memcpy(CMSG_DATA(cmsg), &pidfd_flags, sizeof(pidfd_flags)); + err = sendmsg(pfd, &msg, 0); + ASSERT_NE(-1, err); close(pfd); waitpid(self->client_pid, &child_status, 0); -- 2.47.0

1 year

3
4
0 0

[PATCH net-next v4 0/3] selftests: Add selftest for link layer and performance testing

by Mohan Prasad J

The series of patches are for doing basic tests of NIC driver. Test comprises checks for auto-negotiation, speed, duplex state and throughput between local NIC and partner. Tools such as ethtool, iperf3 are used. Signed-off-by: Mohan Prasad J <mohan.prasad(a)microchip.com> --- Changes in v4: - Type hints are added for arguments and return types. - Test values can be modified through command line. - Minor code improvements. - GenerateTraffic class extended for throughput test. - Protocol testcases separated. Changes in v3: Link to v3: https://patchwork.kernel.org/project/netdevbpf/cover/20241016215014.401476-… - LinkConfig class is included in the hw library. This contains generic APIs for doing link layer operations. - Auto-negotiation checks involve changing the auto-neg state both in local and partner NIC. - Link layer test and performance test are separated to different selftest files. - Resetting of NIC driver done after test completion. Changes in v2: Link to v2: https://patchwork.kernel.org/project/netdevbpf/cover/20240917023525.2571082… - Changed the hardcoded implementation of speed, duplex states, throughput to generic values, in order to support all type of NIC drivers. - Test executes based on the supported link modes between local NIC driver and partner. - Instead of lan743x directory, selftest file is now relocated to /selftests/drivers/net/hw. Link to v1: https://patchwork.kernel.org/project/netdevbpf/cover/20240903221549.1215842… --- Mohan Prasad J (3): selftests: nic_link_layer: Add link layer selftest for NIC driver selftests: nic_link_layer: Add selftest case for speed and duplex states selftests: nic_performance: Add selftest for performance of NIC driver .../testing/selftests/drivers/net/hw/Makefile | 6 +- .../drivers/net/hw/lib/py/__init__.py | 1 + .../drivers/net/hw/lib/py/linkconfig.py | 222 ++++++++++++++++++ .../drivers/net/hw/nic_link_layer.py | 113 +++++++++ .../drivers/net/hw/nic_performance.py | 137 +++++++++++ .../selftests/drivers/net/lib/py/load.py | 20 +- 6 files changed, 496 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py create mode 100644 tools/testing/selftests/drivers/net/hw/nic_link_layer.py create mode 100644 tools/testing/selftests/drivers/net/hw/nic_performance.py -- 2.43.0

1 year

3
5
0 0

[PATCH bpf-next v2 00/13] selftests/bpf: migrate test_flow_dissector.sh to test_progs

by Alexis Lothoré (eBPF Foundation)

Hello, this new series aims to migrate test_flow_dissector.sh into test_progs. There are 2 "main" parts in test_flow_dissector.sh: - a set of tests checking flow_dissector programs attachment to either root namespace or non-root namespace - dissection test The first set is integrated in flow_dissector.c, which already contains some existing tests for flow_dissector programs. This series uses the opportunity to update a bit this file (use new assert, re-split tests, etc) The second part is migrated into a new file under test_progs, flow_dissector_classification.c. It uses the same eBPF programs as flow_dissector.c, but the difference is rather about how those program are executed: - flow_dissector.c manually runs programs with BPF_PROG_RUN - flow_dissector_classification.c sends real packets to be dissected, and so it also executes kernel code related to eBPF flow dissector (eg: __skb_flow_bpf_to_target) --- Changes in v2: - allow tests to run in parallel - move some generic helpers to network_helpers.h - define proper function for ASSERT_MEMEQ - fetch acked-by tags - Link to v1: https://lore.kernel.org/r/20241113-flow_dissector-v1-0-27c4df0592dc@bootlin… --- Alexis Lothoré (eBPF Foundation) (13): selftests/bpf: add a macro to compare raw memory selftests/bpf: use ASSERT_MEMEQ to compare bpf flow keys selftests/bpf: replace CHECK calls with ASSERT macros in flow_dissector test selftests/bpf: re-split main function into dedicated tests selftests/bpf: expose all subtests from flow_dissector selftests/bpf: add gre packets testing to flow_dissector selftests/bpf: migrate flow_dissector namespace exclusivity test selftests/bpf: Enable generic tc actions in selftests config selftests/bpf: move ip checksum helper to network helpers selftests/bpf: rename pseudo headers checksum computation selftests/bpf: add network helpers to generate udp checksums selftests/bpf: migrate bpf flow dissectors tests to test_progs selftests/bpf: remove test_flow_dissector.sh tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/config | 1 + tools/testing/selftests/bpf/network_helpers.h | 64 +- .../selftests/bpf/prog_tests/flow_dissector.c | 323 +++++++-- .../bpf/prog_tests/flow_dissector_classification.c | 807 +++++++++++++++++++++ .../selftests/bpf/prog_tests/xdp_metadata.c | 24 +- tools/testing/selftests/bpf/test_flow_dissector.c | 780 -------------------- tools/testing/selftests/bpf/test_flow_dissector.sh | 178 ----- tools/testing/selftests/bpf/test_progs.c | 15 + tools/testing/selftests/bpf/test_progs.h | 15 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 12 +- 12 files changed, 1153 insertions(+), 1070 deletions(-) --- base-commit: 9e71d50d3befb93a6394b0979f8ebd0dc9bd8d0f change-id: 20241019-flow_dissector-3eb0c07fc163 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

1 year

3
24
0 0

[PATCH net 0/2] ipv6: fix temporary address not removed correctly

by Hangbin Liu

Currently the temporary address is not removed when mngtmpaddr is deleted or becomes unmanaged. The patch set fixed this issue and add a related test. Hangbin Liu (2): net/ipv6: delete temporary address if mngtmpaddr is removed or un-mngtmpaddr selftests/rtnetlink.sh: add mngtempaddr test net/ipv6/addrconf.c | 5 ++ tools/testing/selftests/net/rtnetlink.sh | 89 ++++++++++++++++++++++++ 2 files changed, 94 insertions(+) -- 2.46.0

1 year

4
17
0 0

[PATCH v2] kunit: string-stream: Fix a UAF bug in kunit_init_suite()

by Jinjie Ruan

In kunit_debugfs_create_suite(), if alloc_string_stream() fails in the kunit_suite_for_each_test_case() loop, the "suite->log = stream" has assigned before, and the error path only free the suite->log's stream memory but not set it to NULL, so the later string_stream_clear() of suite->log in kunit_init_suite() will cause below UAF bug. Set stream pointer to NULL after free to fix it. Unable to handle kernel paging request at virtual address 006440150000030d Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [006440150000030d] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: iio_test_gts industrialio_gts_helper cfg80211 rfkill ipv6 [last unloaded: iio_test_gts] CPU: 5 UID: 0 PID: 6253 Comm: modprobe Tainted: G B W N 6.12.0-rc4+ #458 Tainted: [B]=BAD_PAGE, [W]=WARN, [N]=TEST Hardware name: linux,dummy-virt (DT) pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : string_stream_clear+0x54/0x1ac lr : string_stream_clear+0x1a8/0x1ac sp : ffffffc080b47410 x29: ffffffc080b47410 x28: 006440550000030d x27: ffffff80c96b5e98 x26: ffffff80c96b5e80 x25: ffffffe461b3f6c0 x24: 0000000000000003 x23: ffffff80c96b5e88 x22: 1ffffff019cdf4fc x21: dfffffc000000000 x20: ffffff80ce6fa7e0 x19: 032202a80000186d x18: 0000000000001840 x17: 0000000000000000 x16: 0000000000000000 x15: ffffffe45c355cb4 x14: ffffffe45c35589c x13: ffffffe45c03da78 x12: ffffffb810168e75 x11: 1ffffff810168e74 x10: ffffffb810168e74 x9 : dfffffc000000000 x8 : 0000000000000004 x7 : 0000000000000003 x6 : 0000000000000001 x5 : ffffffc080b473a0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000001 x1 : ffffffe462fbf620 x0 : dfffffc000000000 Call trace: string_stream_clear+0x54/0x1ac __kunit_test_suites_init+0x108/0x1d8 kunit_exec_run_tests+0xb8/0x100 kunit_module_notify+0x400/0x55c notifier_call_chain+0xfc/0x3b4 blocking_notifier_call_chain+0x68/0x9c do_init_module+0x24c/0x5c8 load_module+0x4acc/0x4e90 init_module_from_file+0xd4/0x128 idempotent_init_module+0x2d4/0x57c __arm64_sys_finit_module+0xac/0x100 invoke_syscall+0x6c/0x258 el0_svc_common.constprop.0+0x160/0x22c do_el0_svc+0x44/0x5c el0_svc+0x48/0xb8 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 Code: f9400753 d2dff800 f2fbffe0 d343fe7c (38e06b80) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception Cc: stable(a)vger.kernel.org Fixes: a3fdf784780c ("kunit: string-stream: Decouple string_stream from kunit") Suggested-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- v2: - Correct the fix way. - Add Suggested-by. --- lib/kunit/debugfs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..b25d214b93e1 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -212,8 +212,11 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) err: string_stream_destroy(suite->log); - kunit_suite_for_each_test_case(suite, test_case) + suite->log = NULL; + kunit_suite_for_each_test_case(suite, test_case) { string_stream_destroy(test_case->log); + test_case->log = NULL; + } } void kunit_debugfs_destroy_suite(struct kunit_suite *suite) -- 2.34.1

1 year

3
3
0 0

[PATCH bpf v4 0/2] bpf: fix recursive lock and add test

by Jiayuan Chen

1. fix recursive lock when ebpf prog return SK_PASS. 2. add selftest to reproduce recursive lock. Note that the test code can reproduce the 'dead-lock' and if just the selftest merged without first patch, the test case will definitely fail, because the issue of deadlock is inevitable. --- v2->v4: fix line length reported by patchwork and remove unused code. (max_line_length is set to 80 in patchwork but default is 100 in kernel tree) v1->v2: 1.inspired by martin.lau to add selftest to reproduce the issue. 2. follow the community rules for patch. v1: https://lore.kernel.org/bpf/55fc6114-7e64-4b65-86d2-92cfd1e9e92f@linux.dev/… --- Jiayuan Chen (2): bpf: fix recursive lock when verdict program return SK_PASS selftests/bpf: Add some tests with sockmap SK_PASS net/core/skmsg.c | 4 +- .../selftests/bpf/prog_tests/sockmap_basic.c | 54 +++++++++++++++++++ 2 files changed, 56 insertions(+), 2 deletions(-) -- 2.43.5

1 year

3
4
0 0

[PATCH v1] selftests/bpf: fix application of sizeof to pointer

by guanjing

sizeof when applied to a pointer typed expression gives the size of the pointer. tools/testing/selftests/bpf/progs/test_tunnel_kern.c:678:41-47: ERROR: application of sizeof to pointer The proper fix in this particular case is to code sizeof(*gopt) instead of sizeof(gopt). This issue was detected with the help of Coccinelle. Fixes: 5ddafcc377f9 ("selftests/bpf: Fix a few tests for GCC related warnings.") Signed-off-by: guanjing <guanjing(a)cmss.chinamobile.com> --- tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 32127f1cd687..3a437cdc5c15 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -675,7 +675,7 @@ int ip6geneve_set_tunnel(struct __sk_buff *skb) gopt->length = 2; /* 4-byte multiple */ *(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef); - ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); + ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(*gopt)); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; -- 2.33.0

1 year

2
1
0 0

[PATCH net-next] selftests: net: netlink-dumps: validation checks

by Jakub Kicinski

The sanity checks are going to get silently cast to unsigned and always pass. Cast the sizeof to signed size. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/netlink-dumps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 195febbf6a61..07423f256f96 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -185,10 +185,10 @@ TEST(test_sanity) ASSERT_EQ(n, sizeof(dump_policies)); n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); - ASSERT_GE(n, sizeof(struct nlmsghdr)); + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); - ASSERT_GE(n, sizeof(struct nlmsghdr)); + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); close(netlink_sock); } -- 2.47.0

1 year

3
2
0 0

[PATCH net-next] mm: page_frag: fix a compile error when kernel is not compiled

by Yunsheng Lin

page_frag test module is an out of tree module, but built using KDIR as the main kernel tree, the mm test suite is just getting skipped if newly added page_frag test module fails to compile due to kernel not yet compiled. Fix the above problem by ensuring both kernel is built first and a newer kernel which has page_frag_cache.h is used. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexanderduyck(a)fb.com> CC: Linux-MM <linux-mm(a)kvack.org> Fixes: 7fef0dec415c ("mm: page_frag: add a test module for page_frag") Fixes: 65941f10caf2 ("mm: move the page fragment allocator from page_alloc into its own file") Reported-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Yunsheng Lin <yunshenglin0825(a)gmail.com> --- Mote, page_frag test module is only in the net-next tree for now, so target the net-next tree. --- tools/testing/selftests/mm/Makefile | 18 ++++++++++++++++++ tools/testing/selftests/mm/page_frag/Makefile | 2 +- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index acec529baaca..04e04733fc8a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,7 +36,16 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +KDIR ?= /lib/modules/$(shell uname -r)/build +ifneq (,$(wildcard $(KDIR)/Module.symvers)) +ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) TEST_GEN_MODS_DIR := page_frag +else +PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel" +endif +else +PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first" +endif TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test @@ -214,3 +223,12 @@ warn_missing_liburing: echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif + +ifneq ($(PAGE_FRAG_WARNING),) +all: warn_missing_page_frag + +warn_missing_page_frag: + @echo ; \ + echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \ + echo +endif diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile index 58dda74d50a3..8c8bb39ffa28 100644 --- a/tools/testing/selftests/mm/page_frag/Makefile +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -1,5 +1,5 @@ PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) +KDIR ?= /lib/modules/$(shell uname -r)/build ifeq ($(V),1) Q = -- 2.34.1

1 year

3
3
0 0

[RFC PATCH net-next 11/11] selftests: forwarding: Add a selftest for the new reserved_bits UAPI

by Petr Machata

Run VXLAN packets through a gateway. Flip individual bits of the packet and/or reserved bits of the gateway, and check that the gateway treats the packets as expected. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org .../net/forwarding/vxlan_reserved.sh | 352 ++++++++++++++++++ 1 file changed, 352 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/vxlan_reserved.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh new file mode 100755 index 000000000000..46c31794b91b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh @@ -0,0 +1,352 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|--------------------------------+ +# | SW | | +# | +--|------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +---------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +--|----------------------------------+ +# | +# +--|----------------------------------+ +# | | | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# | VRP2 (vrf) | +# +-------------------------------------+ + +: ${VXPORT:=4789} +: ${ALL_TESTS:=" + default_test + plain_test + reserved_0_test + reserved_10_test + reserved_31_test + reserved_56_test + reserved_63_test + "} + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + defer simple_if_fini $h1 192.0.2.1/28 + + tc qdisc add dev $h1 clsact + defer tc qdisc del dev $h1 clsact + + tc filter add dev $h1 ingress pref 77 \ + prot ip flower skip_hw ip_proto icmp action drop + defer tc filter del dev $h1 ingress pref 77 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip_link_set_addr br1 $(mac_get $swp1) + ip_link_set_up br1 + + ip_link_set_up $rp1 + ip_addr_add $rp1 192.0.2.17/28 + ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18 + + ip_link_set_master $swp1 br1 + ip_link_set_up $swp1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + defer simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + h1_create + switch_create + + vrp2_create +} + +vxlan_header_bytes() +{ + local vni=$1; shift + local -a extra_bits=("$@") + local -a bits + local i + + for ((i=0; i < 64; i++)); do + bits[i]=0 + done + + # Bit 4 is the I flag and is always on. + bits[4]=1 + + for i in ${extra_bits[@]}; do + bits[i]=1 + done + + # Bits 32..55 carry the VNI + local mask=0x800000 + for ((i=0; i < 24; i++)); do + bits[$((i + 32))]=$(((vni & mask) != 0)) + ((mask >>= 1)) + done + + local bytes + for ((i=0; i < 8; i++)); do + local byte=0 + local j + for ((j=0; j < 8; j++)); do + local bit=${bits[8 * i + j]} + ((byte += bit << (7 - j))) + done + bytes+=$(printf %02x $byte): + done + + echo ${bytes%:} +} + +neg_bytes() +{ + local bytes=$1; shift + + local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8 + [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:) + local out + local i + + for ((i=0; i < ${#bytes}; i++)); do + local c=${bytes:$i:1} + out+=${neg[$c]} + done + echo $out +} + +vxlan_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local vni=$1; shift + local reserved_bits=$1; shift + + local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits) + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp sp=23456,dp=$VXPORT,p=$(: + )"$vxlan_header:"$( : VXLAN + )"$dest_mac:"$( : ETH daddr + )"00:11:22:33:44:55:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr + )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request seq. number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} + +vxlan_device_add() +{ + ip_link_add vx1 up type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 "$@" + ip_link_set_master vx1 br1 +} + +vxlan_all_reserved_bits() +{ + local i + + for ((i=0; i < 64; i++)); do + if ((i == 4 || i >= 32 && i < 56)); then + continue + fi + echo $i + done +} + +vxlan_ping_vanilla() +{ + vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000 +} + +vxlan_ping_reserved() +{ + for bit in $(vxlan_all_reserved_bits); do + vxlan_ping_do 1 $rp2 $(mac_get $rp1) \ + 192.0.2.17 $(mac_get $h1) 1000 "$bit" + ((n++)) + done +} + +vxlan_ping_test() +{ + local what=$1; shift + local get_stat=$1; shift + local expect=$1; shift + + RET=0 + + local t0=$($get_stat) + + "$@" + check_err $? "Failure when running $@" + + local t1=$($get_stat) + local delta=$((t1 - t0)) + + ((expect == delta)) + check_err $? "Expected to capture $expect packets, got $delta." + + log_test "$what" +} + +__default_test_do() +{ + local n_allowed_bits=$1; shift + local what=$1; shift + + vxlan_ping_test "$what: clean packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + 10 vxlan_ping_vanilla + + local t0=$(link_stats_get vx1 rx errors) + vxlan_ping_test "$what: mangled packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + $n_allowed_bits vxlan_ping_reserved + local t1=$(link_stats_get vx1 rx errors) + + RET=0 + local expect=$((39 - n_allowed_bits)) + local delta=$((t1 - t0)) + ((expect == delta)) + check_err $? "Expected $expect error packets, got $delta." + log_test "$what: drops reported" +} + +default_test_do() +{ + vxlan_device_add + __default_test_do 0 "Default" +} + +default_test() +{ + in_defer_scope \ + default_test_do +} + +plain_test_do() +{ + vxlan_device_add reserved_bits 0xf7ffffff000000ff + __default_test_do 0 "reserved_bits 0xf7ffffff000000ff" +} + +plain_test() +{ + in_defer_scope \ + plain_test_do +} + +reserved_test() +{ + local bit=$1; shift + + local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit) + local reserved_bytes=$(neg_bytes $allowed_bytes) + local reserved_bits=${reserved_bytes//:/} + + vxlan_device_add reserved_bits 0x$reserved_bits + __default_test_do 1 "reserved_bits 0x$reserved_bits" +} + +reserved_0_test() +{ + in_defer_scope \ + reserved_test 0 +} + +reserved_10_test() +{ + in_defer_scope \ + reserved_test 10 +} + +reserved_31_test() +{ + in_defer_scope \ + reserved_test 31 +} + +reserved_56_test() +{ + in_defer_scope \ + reserved_test 56 +} + +reserved_63_test() +{ + in_defer_scope \ + reserved_test 63 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS -- 2.47.0

1 year

1
0
0 0

[RFC PATCH net-next 10/11] selftests: net: lib: Add several autodefer helpers

by Petr Machata

Add ip_link_set_addr(), ip_link_set_up(), ip_addr_add() and ip_route_add() to the suite of helpers that automatically schedule a corresponding cleanup. When setting a new MAC, one needs to remember the old address first. Move mac_get() from forwarding/ to that end. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org tools/testing/selftests/net/forwarding/lib.sh | 7 ---- tools/testing/selftests/net/lib.sh | 39 +++++++++++++++++++ 2 files changed, 39 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..1fd40bada694 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -932,13 +932,6 @@ packets_rate() echo $(((t1 - t0) / interval)) } -mac_get() -{ - local if_name=$1 - - ip -j link show dev $if_name | jq -r '.[]["address"]' -} - ether_addr_to_u64() { local addr="$1" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 5ea6537acd2b..2cd5c743b2d9 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -435,6 +435,13 @@ xfail_on_veth() fi } +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + kill_process() { local pid=$1; shift @@ -459,3 +466,35 @@ ip_link_set_master() ip link set dev "$member" master "$master" defer ip link set dev "$member" nomaster } + +ip_link_set_addr() +{ + local name=$1; shift + local addr=$1; shift + + local old_addr=$(mac_get "$name") + ip link set dev "$name" address "$addr" + defer ip link set dev "$name" address "$old_addr" +} + +ip_link_set_up() +{ + local name=$1; shift + + ip link set dev "$name" up + defer ip link set dev "$name" down +} + +ip_addr_add() +{ + local name=$1; shift + + ip addr add dev "$name" "$@" + defer ip addr del dev "$name" "$@" +} + +ip_route_add() +{ + ip route add "$@" + defer ip route del "$@" +} -- 2.47.0

1 year

1
0
0 0

[RFC PATCH net-next 09/11] selftests: net: lib: Rename ip_link_master() to ip_link_set_master()

by Petr Machata

Let's have a verb in that function name to make it clearer what's going on. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org tools/testing/selftests/net/fdb_notify.sh | 6 +++--- tools/testing/selftests/net/lib.sh | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh index c03151e7791c..c159230c9b62 100755 --- a/tools/testing/selftests/net/fdb_notify.sh +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -49,7 +49,7 @@ test_dup_vxlan_self() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan" dev vx self dst 192.0.2.1 do_test_dup del "vxlan" dev vx self dst 192.0.2.1 @@ -59,7 +59,7 @@ test_dup_vxlan_master() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan master" dev vx master do_test_dup del "vxlan master" dev vx master @@ -79,7 +79,7 @@ test_dup_macvlan_master() ip_link_add br up type bridge vlan_filtering 1 ip_link_add dd up type dummy ip_link_add mv up link dd type macvlan mode passthru - ip_link_master mv br + ip_link_set_master mv br do_test_dup add "macvlan master" dev mv self do_test_dup del "macvlan master" dev mv self diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8994fec1c38f..5ea6537acd2b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -451,7 +451,7 @@ ip_link_add() defer ip link del dev "$name" } -ip_link_master() +ip_link_set_master() { local member=$1; shift local master=$1; shift -- 2.47.0

1 year

1
0
0 0

[PATCH] selftests/bpf: Remove unused variable

by Zhu Jun

the variable is never referenced in the code, just remove them. Signed-off-by: Zhu Jun <zhujun2(a)cmss.chinamobile.com> --- tools/testing/selftests/bpf/prog_tests/log_buf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 27676a04d0b6..5d1678b15d8b 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -191,7 +191,6 @@ static void bpf_prog_load_log_buf(void) ASSERT_LT(fd, 0, "bad_fd"); if (fd >= 0) close(fd); - fd = -1; free(log_buf); } @@ -259,7 +258,6 @@ static void bpf_btf_load_log_buf(void) ASSERT_LT(fd, 0, "bad_fd"); if (fd >= 0) close(fd); - fd = -1; cleanup: free(log_buf); -- 2.17.1

1 year

2
1
0 0

[PATCH] kvm: hardware_disable_test: remove unused macro

by Ba Jing

After reviewing the code, it was found that the macro GUEST_CODE_PIO_PORT is never referenced in the code. Just remove it. Signed-off-by: Ba Jing <bajing(a)cmss.chinamobile.com> --- tools/testing/selftests/kvm/hardware_disable_test.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index bce73bcb973c..94bd6ed24cf3 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -20,7 +20,6 @@ #define SLEEPING_THREAD_NUM (1 << 4) #define FORK_NUM (1ULL << 9) #define DELAY_US_MAX 2000 -#define GUEST_CODE_PIO_PORT 4 sem_t *sem; -- 2.33.0

1 year

2
1
0 0

[PATCH v2 0/5] Improve arm64 pkeys handling in signal delivery

by Kevin Brodsky

This series is a follow-up to Joey's Permission Overlay Extension (POE) series [1] that recently landed on mainline. The goal is to improve the way we handle the register that governs which pkeys/POIndex are accessible (POR_EL0) during signal delivery. As things stand, we may unexpectedly fail to write the signal frame on the stack because POR_EL0 is not reset before the uaccess operations. See patch 3 for more details and the main changes this series brings. A similar series landed recently for x86/MPK [2]; the present series aims at aligning arm64 with x86. Worth noting: once the signal frame is written, POR_EL0 is still set to POR_EL0_INIT, granting access to pkey 0 only. This means that a program that sets up an alternate signal stack with a non-zero pkey will need some assembly trampoline to set POR_EL0 before invoking the real signal handler, as discussed here [3]. This is not ideal, but it makes experimentation with pkeys in signal handlers possible while waiting for a potential interface to control the pkey state when delivering a signal. See Pierre's reply [4] for more information about use-cases and a potential interface. The x86 series also added kselftests to ensure that no spurious SIGSEGV occurs during signal delivery regardless of which pkey is accessible at the point where the signal is delivered. This series adapts those kselftests to allow running them on arm64 (patch 4-5). Finally patch 2 is a clean-up following feedback on Joey's series [5]. I have tested this series on arm64 and x86_64 (booting and running the protection_keys and pkey_sighandler_tests mm kselftests). v1..v2: * In setup_rt_frame(), ensured that POR_EL0 is reset to its original value if we fail to deliver the signal (addresses Catalin's concern [6]). * Renamed *unpriv_access* to *user_access* in patch 3 (suggestion from Dave). * Made what patch 1-2 do explicit in the commit message body (suggestion from Dave). - Kevin [1] https://lore.kernel.org/linux-arm-kernel/20240822151113.1479789-1-joey.goul… [2] https://lore.kernel.org/lkml/20240802061318.2140081-1-aruna.ramakrishna@ora… [3] https://lore.kernel.org/lkml/CABi2SkWxNkP2O7ipkP67WKz0-LV33e5brReevTTtba6oK… [4] https://lore.kernel.org/linux-arm-kernel/87plns8owh.fsf@arm.com/ [5] https://lore.kernel.org/linux-arm-kernel/20241015114116.GA19334@willie-the-… [6] https://lore.kernel.org/linux-arm-kernel/Zw6D2waVyIwYE7wd@arm.com/ Cc: akpm(a)linux-foundation.org Cc: anshuman.khandual(a)arm.com Cc: aruna.ramakrishna(a)oracle.com Cc: broonie(a)kernel.org Cc: catalin.marinas(a)arm.com Cc: dave.hansen(a)linux.intel.com Cc: dave.martin(a)arm.com Cc: jeffxu(a)chromium.org Cc: joey.gouly(a)arm.com Cc: pierre.langlois(a)arm.com Cc: shuah(a)kernel.org Cc: sroettger(a)google.com Cc: will(a)kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: x86(a)kernel.org Kevin Brodsky (5): arm64: signal: Remove unused macro arm64: signal: Remove unnecessary check when saving POE state arm64: signal: Improve POR_EL0 handling to avoid uaccess failures selftests/mm: Use generic pkey register manipulation selftests/mm: Enable pkey_sighandler_tests on arm64 arch/arm64/kernel/signal.c | 95 +++++++++++++--- tools/testing/selftests/mm/Makefile | 8 +- tools/testing/selftests/mm/pkey-arm64.h | 1 + tools/testing/selftests/mm/pkey-x86.h | 2 + .../selftests/mm/pkey_sighandler_tests.c | 101 +++++++++++++----- 5 files changed, 162 insertions(+), 45 deletions(-) -- 2.43.0

1 year

4
18
0 0

[PATCH bpf-next/net 0/5] bpf: Add mptcp_subflow bpf_iter support

by Matthieu Baerts (NGI0)

Here is a series from Geliang, adding mptcp_subflow bpf_iter support. We are working on extending MPTCP with BPF, e.g. to control the path manager -- in charge of the creation, deletion, and announcements of subflows (paths) -- and the packet scheduler -- in charge of selecting which available path the next data will be sent to. These extensions need to iterate over the list of subflows attached to an MPTCP connection, and do some specific actions via some new kfunc that will be added later on. This preparation work is split in different patches: - Patch 1: register some "basic" MPTCP kfunc. - Patch 2: add mptcp_subflow bpf_iter support. Note that previous versions of this single patch have already been shared to the BPF mailing list. The changelog has been kept with a comment, but the version number has been reset to avoid confusions. - Patch 3: add kfunc to make sure the msk is valid - Patch 4: add more MPTCP endpoints in the selftests, in order to create more than 2 subflows. - Patch 5: add a very simple test validating mptcp_subflow bpf_iter support. This test could be written without the new bpf_iter, but it is there only to make sure this specific feature works as expected. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (5): bpf: Register mptcp common kfunc set bpf: Add mptcp_subflow bpf_iter bpf: Acquire and release mptcp socket selftests/bpf: More endpoints for endpoint_init selftests/bpf: Add mptcp_subflow bpf_iter subtest net/mptcp/bpf.c | 104 ++++++++++++++++- tools/testing/selftests/bpf/bpf_experimental.h | 8 ++ tools/testing/selftests/bpf/prog_tests/mptcp.c | 129 ++++++++++++++++++++- tools/testing/selftests/bpf/progs/mptcp_bpf.h | 10 ++ .../testing/selftests/bpf/progs/mptcp_bpf_iters.c | 64 ++++++++++ 5 files changed, 308 insertions(+), 7 deletions(-) --- base-commit: 141b4d6a8049cecdc8124f87e044b83a9e80730d change-id: 20241108-bpf-next-net-mptcp-bpf_iter-subflows-027f6d87770e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year

3
9
0 0

[PATCH v7 00/13] iommufd: Add vIOMMU infrastructure (Part-1)

by Nicolin Chen

This series introduces a new vIOMMU infrastructure and related ioctls. IOMMUFD has been using the HWPT infrastructure for all cases, including a nested IO page table support. Yet, there're limitations for an HWPT-based structure to support some advanced HW-accelerated features, such as CMDQV on NVIDIA Grace, and HW-accelerated vIOMMU on AMD. Even for a multi-IOMMU environment, it is not straightforward for nested HWPTs to share the same parent HWPT (stage-2 IO pagetable), with the HWPT infrastructure alone: a parent HWPT typically hold one stage-2 IO pagetable and tag it with only one ID in the cache entries. When sharing one large stage-2 IO pagetable across physical IOMMU instances, that one ID may not always be available across all the IOMMU instances. In other word, it's ideal for SW to have a different container for the stage-2 IO pagetable so it can hold another ID that's available. And this container will be able to hold some advanced feature too. For this "different container", add vIOMMU, an additional layer to hold extra virtualization information: _______________________________________________________________________ | iommufd (with vIOMMU) | | _____________ | | | | | | |----------------| vIOMMU | | | | ______ | | _____________ ________ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | | | | | | | | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| The vIOMMU object should be seen as a slice of a physical IOMMU instance that is passed to or shared with a VM. That can be some HW/SW resources: - Security namespace for guest owned ID, e.g. guest-controlled cache tags - Non-device-affiliated event reporting, e.g. invalidation queue errors - Access to a sharable nesting parent pagetable across physical IOMMUs - Virtualization of various platforms IDs, e.g. RIDs and others - Delivery of paravirtualized invalidation - Direct assigned invalidation queues - Direct assigned interrupts On a multi-IOMMU system, the vIOMMU object must be instanced to the number of the physical IOMMUs that have a slice passed to (via device) a guest VM, while being able to hold the shareable parent HWPT. Each vIOMMU then just needs to allocate its own individual ID to tag its own cache: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | IDx | ---------------------------- ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested1 |--->| viommu1 ------------------ ---------------- | | IDy | ---------------------------- As an initial part-1, add IOMMUFD_CMD_VIOMMU_ALLOC ioctl for an allocation only. More vIOMMU-based structs and ioctls will be introduced in the follow-up series to support vDEVICE, vIRQ (vEVENT) and vQUEUE objects. Although we repurposed the vIOMMU object from an earlier RFC, just for a referece: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p1-v7 (QEMU branch for testing will be provided in Jason's nesting series) Changelog v7 * Added "Reviewed-by" from Jason * Dropped "select IOMMUFD_DRIVER_CORE" in Kconfig * Decoupled IOMMUFD_DRIVER from IOMMUFD_DRIVER_CORE * Moved vIOMMU negative tests out of FIXTURE_SETUP to a TEST_F * Dropped the "flags" check in iommufd_viommu_alloc_hwpt_nested * Added the kdoc for "flags" in iommufd_viommu_alloc_hwpt_nested v6 https://lore.kernel.org/all/cover.1730313237.git.nicolinc@nvidia.com/ * Improved comment lines * Added a TEST_F for IO page fault * Fixed indentations in iommufd.rst * Revised kdoc of the viommu_alloc op * Added "Reviewed-by" from Kevin and Jason * Passed in "flags" to ->alloc_domain_nested * Renamed "free" op to "destroy" in viommu_ops * Skipped SMMUv3 driver changes (to post in a separate series) * Fixed "flags" validation in iommufd_viommu_alloc_hwpt_nested * Added CONFIG_IOMMUFD_DRIVER_CORE for sharing between iommufd core and IOMMU dirvers * Replaced iommufd_verify_unfinalized_object with xa_cmpxchg in iommufd_object_finalize/abort functions v5 https://lore.kernel.org/all/cover.1729897352.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Kevin * Reworked iommufd_viommu_alloc helper * Revised the uAPI kdoc for vIOMMU object * Revised comments for pluggable iommu_dev * Added a couple of cleanup patches for selftest * Renamed domain_alloc_nested op to alloc_domain_nested * Updated a few commit messages to reflect the latest series * Renamed iommufd_hwpt_nested_alloc_for_viommu to iommufd_viommu_alloc_hwpt_nested, and added flag validation v4 https://lore.kernel.org/all/cover.1729553811.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Jason * Dropped IOMMU_VIOMMU_TYPE_DEFAULT support * Dropped iommufd_object_alloc_elm renamings * Renamed iommufd's viommu_api.c to driver.c * Reworked iommufd_viommu_alloc helper * Added a separate iommufd_hwpt_nested_alloc_for_viommu function for hwpt_nested allocations on a vIOMMU, and added comparison between viommu->iommu_dev->ops and dev_iommu_ops(idev->dev) * Replaced s2_parent with vsmmu in arm_smmu_nested_domain * Replaced domain_alloc_user in iommu_ops with domain_alloc_nested in viommu_ops * Replaced wait_queue_head_t with a completion, to delay the unplug of mock_iommu_dev * Corrected documentation graph that was missing struct iommu_device * Added an iommufd_verify_unfinalized_object helper to verify driver- allocated vIOMMU/vDEVICE objects * Added missing test cases for TEST_LENGTH and fail_nth v3 https://lore.kernel.org/all/cover.1728491453.git.nicolinc@nvidia.com/ * Rebased on top of Jason's nesting v3 series https://lore.kernel.org/all/0-v3-e2e16cd7467f+2a6a1-smmuv3_nesting_jgg@nvid… * Split the series into smaller parts * Added Jason's Reviewed-by * Added back viommu->iommu_dev * Added support for driver-allocated vIOMMU v.s. core-allocated * Dropped arm_smmu_cache_invalidate_user * Added an iommufd_test_wait_for_users() in selftest * Reworked test code to make viommu an individual FIXTURE * Added missing TEST_LENGTH case for the new ioctl command v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (13): iommufd: Move struct iommufd_object to public iommufd header iommufd: Move _iommufd_object_alloc helper to a sharable file iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct iommufd: Verify object in iommufd_object_finalize/abort() iommufd/viommu: Add IOMMU_VIOMMU_ALLOC ioctl iommufd: Add alloc_domain_nested op to iommufd_viommu_ops iommufd: Allow pt_id to carry viommu_id for IOMMU_HWPT_ALLOC iommufd/selftest: Add container_of helpers iommufd/selftest: Prepare for mock_viommu_alloc_domain_nested() iommufd/selftest: Add refcount to mock_iommu_device iommufd/selftest: Add IOMMU_VIOMMU_TYPE_SELFTEST iommufd/selftest: Add IOMMU_VIOMMU_ALLOC test coverage Documentation: userspace-api: iommufd: Update vIOMMU drivers/iommu/iommufd/Kconfig | 4 + drivers/iommu/iommufd/Makefile | 4 +- drivers/iommu/iommufd/iommufd_private.h | 33 +-- drivers/iommu/iommufd/iommufd_test.h | 2 + include/linux/iommu.h | 14 + include/linux/iommufd.h | 86 ++++++ include/uapi/linux/iommufd.h | 54 +++- tools/testing/selftests/iommu/iommufd_utils.h | 28 ++ drivers/iommu/iommufd/driver.c | 40 +++ drivers/iommu/iommufd/hw_pagetable.c | 73 ++++- drivers/iommu/iommufd/main.c | 54 ++-- drivers/iommu/iommufd/selftest.c | 266 +++++++++++++----- drivers/iommu/iommufd/viommu.c | 81 ++++++ tools/testing/selftests/iommu/iommufd.c | 137 +++++++++ .../selftests/iommu/iommufd_fail_nth.c | 11 + Documentation/userspace-api/iommufd.rst | 69 ++++- 16 files changed, 804 insertions(+), 152 deletions(-) create mode 100644 drivers/iommu/iommufd/driver.c create mode 100644 drivers/iommu/iommufd/viommu.c base-commit: 0bcceb1f51c77f6b98a7aab00847ed340bf36e35 -- 2.43.0

1 year

4
28
0 0

[PATCHv2 net] selftests: wireguard: load nf_conntrack if it's not present

by Hangbin Liu

Some distros may not load nf_conntrack by default, which will cause subsequent nf_conntrack settings to fail. Let's load this module if it's not loaded by default. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v2: load the mode directly in case nf_conntrack is build in (Simon Horman) --- tools/testing/selftests/wireguard/netns.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..fa4dd7eb5918 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -66,6 +66,7 @@ cleanup() { orig_message_cost="$(< /proc/sys/net/core/message_cost)" trap cleanup EXIT printf 0 > /proc/sys/net/core/message_cost +modprobe nf_conntrack ip netns del $netns0 2>/dev/null || true ip netns del $netns1 2>/dev/null || true -- 2.39.5 (Apple Git-154)

1 year

3
2
0 0

[PATCH] selftests/livepatch: Check if CONFIG_LIVEPATCH is enabled

by Siddharth Menon

When CONFIG_LIVEPATCH is disabled, compilation fails due to the required structs from the livepatch header file being undefined. This checks for CONFIG_LIVEPATCH in order to verify that it is enabled before compiling livepatch self-tests. Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Siddharth Menon <simeddon(a)gmail.com> --- tools/testing/selftests/livepatch/test_modules/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile index e6e638c4bcba..b34b80544709 100644 --- a/tools/testing/selftests/livepatch/test_modules/Makefile +++ b/tools/testing/selftests/livepatch/test_modules/Makefile @@ -1,5 +1,6 @@ TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) KDIR ?= /lib/modules/$(shell uname -r)/build +CONFIG_LIVEPATCH := $(shell cd $(KDIR) && scripts/config --state CONFIG_LIVEPATCH) obj-m += test_klp_atomic_replace.o \ test_klp_callbacks_busy.o \ @@ -13,10 +14,15 @@ obj-m += test_klp_atomic_replace.o \ test_klp_shadow_vars.o \ test_klp_syscall.o -# Ensure that KDIR exists, otherwise skip the compilation + +# Ensure that KDIR exists and CONFIG_LIVEPATCH is enabled, else skip compilation modules: ifneq ("$(wildcard $(KDIR))", "") +ifneq ($(filter y m,$(CONFIG_LIVEPATCH)),) $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR) +else + $(warning CONFIG_LIVEPATCH is not enabled in the kernel config file.) +endif endif # Ensure that KDIR exists, otherwise skip the clean target -- 2.39.5

1 year

4
3
0 0

[PATCH 1/5] selftests/powerpc: Lower run time of count_stcx_fail test

by Michael Ellerman

The count_stcx_fail test runs for close to or just over 2 minutes, which means it sometimes times out. That's overkill for a test that just demonstrates some PMU counters are working. Drop the 64 billion instruction case, to lower the runtime to ~30s. Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> --- tools/testing/selftests/powerpc/pmu/count_stcx_fail.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c index 2070a1e2b3a5..d8dd9a9c6c1b 100644 --- a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c +++ b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c @@ -144,9 +144,6 @@ static int test_body(void) /* Run for 16Bi instructions */ FAIL_IF(do_count_loop(events, 16000000000, overhead, true)); - /* Run for 64Bi instructions */ - FAIL_IF(do_count_loop(events, 64000000000, overhead, true)); - event_close(&events[0]); event_close(&events[1]); -- 2.47.0

1 year

2
5
0 0

[PATCH v2] selftests/powerpc: Remove the path after initialization.

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> If there were no anamolies noted, then we can simply remove the log file and return. Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- v1->v2: Remove the path after initialization. tools/testing/selftests/powerpc/mm/tlbie_test.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c index 48344a74b212..35f0098399cc 100644 --- a/tools/testing/selftests/powerpc/mm/tlbie_test.c +++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c @@ -313,16 +313,16 @@ static inline void end_verification_log(unsigned int tid, unsigned nr_anamolies) fclose(f); - if (nr_anamolies == 0) { - remove(path); - return; - } - sprintf(logfile, logfilename, tid); strcpy(path, logdir); strcat(path, separator); strcat(path, logfile); + if (nr_anamolies == 0) { + remove(path); + return; + } + printf("Thread %02d chunk has %d corrupted words. For details check %s\n", tid, nr_anamolies, path); } -- 2.33.0

1 year

3
2
0 0

Nov:16:24

by Van. HR

Hello, I am a private investment consultant representing the interest of a multinational conglomerate that wishes to place funds into a trust management portfolio. Please indicate your interest for additional information. Regards, Van Collin.

1 year

1
0
0 0

[PATCH net-next v23 1/7] mm: page_frag: add a test module for page_frag

by Yunsheng Lin

The testing is done by ensuring that the fragment allocated from a frag_frag_cache instance is pushed into a ptr_ring instance in a kthread binded to a specified cpu, and a kthread binded to a specified cpu will pop the fragment from the ptr_ring and free the fragment. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexander.duyck(a)gmail.com> CC: Linux-MM <linux-mm(a)kvack.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 198 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 175 ++++++++++++++++ 5 files changed, 402 insertions(+) create mode 100644 tools/testing/selftests/mm/page_frag/Makefile create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c create mode 100755 tools/testing/selftests/mm/test_page_frag.sh diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..acec529baaca 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..912d97b99107 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; +static int test_popped; +static int test_pushed; +static bool force_exit; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); + } + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + int last_pushed = 0, last_popped = 0; + ktime_t start; + u64 duration; + int ret; + + test_nc.va = NULL; + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + +out: + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c5797ad1d37b..2c5394584af4 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi + + check_test_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

1 year

4
6
0 0

[PATCH v1] selftest/mm: remove seal_elf

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> Remove seal_elf, which is a demo of mseal, we no longer need this. Signed-off-by: Jeff Xu <jeffxu(a)chromium.org> --- tools/testing/selftests/mm/.gitignore | 1 - tools/testing/selftests/mm/Makefile | 1 - tools/testing/selftests/mm/seal_elf.c | 137 -------------------------- 3 files changed, 139 deletions(-) delete mode 100644 tools/testing/selftests/mm/seal_elf.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..6a273bdbc70b 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -49,7 +49,6 @@ va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test -seal_elf droppable hugetlb_dio pkey_sighandler_tests_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 72ec4403032d..869b6a40f290 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -64,7 +64,6 @@ TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test -TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c deleted file mode 100644 index d9f8ba8d5050..000000000000 --- a/tools/testing/selftests/mm/seal_elf.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <sys/mman.h> -#include <stdint.h> -#include <asm-generic/unistd.h> -#include <string.h> -#include <sys/time.h> -#include <sys/resource.h> -#include <stdbool.h> -#include "../kselftest.h" -#include <syscall.h> -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <sys/vfs.h> -#include <sys/stat.h> -#include "mseal_helpers.h" - -/* - * define sys_xyx to call syscall directly. - */ -static int sys_mseal(void *start, size_t len) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mseal, start, len, 0); - return sret; -} - -static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mprotect, ptr, size, prot); - return sret; -} - -static bool seal_support(void) -{ - int ret; - void *ptr; - unsigned long page_size = getpagesize(); - - ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (ptr == (void *) -1) - return false; - - ret = sys_mseal(ptr, page_size); - if (ret < 0) - return false; - - return true; -} - -const char somestr[4096] = {"READONLY"}; - -static void test_seal_elf(void) -{ - int ret; - FILE *maps; - char line[512]; - uintptr_t addr_start, addr_end; - char prot[5]; - char filename[256]; - unsigned long page_size = getpagesize(); - unsigned long long ptr = (unsigned long long) somestr; - char *somestr2 = (char *)somestr; - - /* - * Modify the protection of readonly somestr - */ - if (((unsigned long long)ptr % page_size) != 0) - ptr = (unsigned long long)ptr & ~(page_size - 1); - - ksft_print_msg("somestr = %s\n", somestr); - ksft_print_msg("change protection to rw\n"); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); - FAIL_TEST_IF_FALSE(!ret); - *somestr2 = 'A'; - ksft_print_msg("somestr is modified to: %s\n", somestr); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ); - FAIL_TEST_IF_FALSE(!ret); - - maps = fopen("/proc/self/maps", "r"); - FAIL_TEST_IF_FALSE(maps); - - /* - * apply sealing to elf binary - */ - while (fgets(line, sizeof(line), maps)) { - if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", - &addr_start, &addr_end, prot, filename) == 4) { - if (strlen(filename)) { - /* - * seal the mapping if read only. - */ - if (strstr(prot, "r-")) { - ret = sys_mseal((void *)addr_start, addr_end - addr_start); - FAIL_TEST_IF_FALSE(!ret); - ksft_print_msg("sealed: %lx-%lx %s %s\n", - addr_start, addr_end, prot, filename); - if ((uintptr_t) somestr >= addr_start && - (uintptr_t) somestr <= addr_end) - ksft_print_msg("mapping for somestr found\n"); - } - } - } - } - fclose(maps); - - ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); - FAIL_TEST_IF_FALSE(ret < 0); - ksft_print_msg("somestr is sealed, mprotect is rejected\n"); - - REPORT_TEST_PASS(); -} - -int main(int argc, char **argv) -{ - bool test_seal = seal_support(); - - ksft_print_header(); - ksft_print_msg("pid=%d\n", getpid()); - - if (!test_seal) - ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); - - ksft_set_plan(1); - - test_seal_elf(); - - ksft_finished(); -} -- 2.47.0.338.g60cca15819-goog

1 year

1
0
0 0

[PATCH net-next v3 0/6] net: Improve netns handling in RTNL and ip_tunnel

by Xiao Liang

This patch series includes some netns-related improvements and fixes for RTNL and ip_tunnel, to make link creation more intuitive: - Creating link in another net namespace doesn't conflict with link names in current one. - Refector rtnetlink link creation. Create link in target namespace directly. Pass both source and link netns to drivers via newlink() callback. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. Patch 1 from Donald is included just as a dependency. --- v3: - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Donald Hunter (1): Revert "tools/net/ynl: improve async notification handling" Xiao Liang (5): net: ip_tunnel: Build flow in underlay net namespace rtnetlink: Lookup device in target netns when creating link rtnetlink: Decouple net namespaces in rtnl_newlink_create() selftests: net: Add python context manager for netns entering selftests: net: Add two test cases for link netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 6 ++- drivers/net/amt.c | 6 +-- drivers/net/bareudp.c | 4 +- drivers/net/bonding/bond_netlink.c | 3 +- drivers/net/can/dev/netlink.c | 2 +- drivers/net/can/vxcan.c | 4 +- .../ethernet/qualcomm/rmnet/rmnet_config.c | 5 +- drivers/net/geneve.c | 4 +- drivers/net/gtp.c | 4 +- drivers/net/ipvlan/ipvlan.h | 2 +- drivers/net/ipvlan/ipvlan_main.c | 5 +- drivers/net/ipvlan/ipvtap.c | 4 +- drivers/net/macsec.c | 5 +- drivers/net/macvlan.c | 5 +- drivers/net/macvtap.c | 5 +- drivers/net/netkit.c | 4 +- drivers/net/pfcp.c | 4 +- drivers/net/ppp/ppp_generic.c | 4 +- drivers/net/team/team_core.c | 2 +- drivers/net/veth.c | 4 +- drivers/net/vrf.c | 2 +- drivers/net/vxlan/vxlan_core.c | 4 +- drivers/net/wireguard/device.c | 4 +- drivers/net/wireless/virtual/virt_wifi.c | 5 +- drivers/net/wwan/wwan_core.c | 6 ++- include/net/ip_tunnels.h | 5 +- include/net/rtnetlink.h | 22 ++++++++- net/8021q/vlan_netlink.c | 5 +- net/batman-adv/soft-interface.c | 5 +- net/bridge/br_netlink.c | 2 +- net/caif/chnl_net.c | 2 +- net/core/rtnetlink.c | 25 ++++++---- net/hsr/hsr_netlink.c | 8 +-- net/ieee802154/6lowpan/core.c | 5 +- net/ipv4/ip_gre.c | 13 +++-- net/ipv4/ip_tunnel.c | 16 +++--- net/ipv4/ip_vti.c | 5 +- net/ipv4/ipip.c | 5 +- net/ipv6/ip6_gre.c | 17 ++++--- net/ipv6/ip6_tunnel.c | 11 ++--- net/ipv6/ip6_vti.c | 11 ++--- net/ipv6/sit.c | 11 ++--- net/xfrm/xfrm_interface_core.c | 13 +++-- tools/net/ynl/cli.py | 10 ++-- tools/net/ynl/lib/ynl.py | 49 ++++++++----------- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++++++ tools/testing/selftests/net/netns-name.sh | 10 ++++ tools/testing/selftests/net/netns_atomic.py | 38 ++++++++++++++ 50 files changed, 255 insertions(+), 157 deletions(-) create mode 100755 tools/testing/selftests/net/netns_atomic.py -- 2.47.0

1 year

2
7
0 0

[PATCH] kunit: debugfs: Use IS_ERR() for alloc_string_stream() error check

by Kuan-Wei Chiu

The alloc_string_stream() function only returns ERR_PTR(-ENOMEM) on failure and never returns NULL. Therefore, switching the error check in the caller from IS_ERR_OR_NULL to IS_ERR improves clarity, indicating that this function will return an error pointer (not NULL) when an error occurs. This change avoids any ambiguity regarding the function's return behavior. Link: https://lore.kernel.org/lkml/Zy9deU5VK3YR+r9N@visitorckw-System-Product-Name Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> --- lib/kunit/debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..6273fa9652df 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -181,7 +181,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) * successfully. */ stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) return; string_stream_set_append_newlines(stream, true); @@ -189,7 +189,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) goto err; string_stream_set_append_newlines(stream, true); -- 2.34.1

1 year

2
1
0 0

[PATCH v2] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> Cc: stable(a)vger.kernel.org --- v2: Add Cc tag. --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

1 year

2
1
0 0

[PATCH v1] MAINTAINERS: Update KUnit email address for Brendan Higgins

by Brendan Higgins

Update Brendan's email address for the KUnit entry. Signed-off-by: Brendan Higgins <brendanhiggins(a)google.com> --- I am leaving Google and am going through and cleaning up my @google.com address in the relevant places. This patch updates my email address for the KUnit entry. I am removing myself from the ASPEED I2C entry in a separate patch. Do note that Friday, November 15 2024 is my last day at Google after which I will lose access to this email account so any future updates or comments after Friday will come from my @linux.dev account. --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b878ddc99f94e..d077a3deeb386 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12405,7 +12405,7 @@ F: fs/smb/common/ F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) -M: Brendan Higgins <brendanhiggins(a)google.com> +M: Brendan Higgins <brendan.higgins(a)linux.dev> M: David Gow <davidgow(a)google.com> R: Rae Moar <rmoar(a)google.com> L: linux-kselftest(a)vger.kernel.org base-commit: cfaaa7d010d1fc58f9717fcc8591201e741d2d49 -- 2.47.0.338.g60cca15819-goog

1 year

2
1
0 0

[RFC PATCH v3 0/6] Direct Map Removal for guest_memfd

by Patrick Roy

Unmapping virtual machine guest memory from the host kernel's direct map is a successful mitigation against Spectre-style transient execution issues: If the kernel page tables do not contain entries pointing to guest memory, then any attempted speculative read through the direct map will necessarily be blocked by the MMU before any observable microarchitectural side-effects happen. This means that Spectre-gadgets and similar cannot be used to target virtual machine memory. Roughly 60% of speculative execution issues fall into this category [1, Table 1]. This patch series extends guest_memfd with the ability to remove its memory from the host kernel's direct map, to be able to attain the above protection for KVM guests running inside guest_memfd. === Changes to v2 === - Handle direct map removal for physically contiguous pages in arch code (Mike R.) - Track the direct map state in guest_memfd itself instead of at the folio level, to prepare for huge pages support (Sean C.) - Allow configuring direct map state of not-yet faulted in memory (Vishal A.) - Pay attention to alignment in ftrace structs (Steven R.) Most significantly, I've reduced the patch series to focus only on direct map removal for guest_memfd for now, leaving the whole "how to do non-CoCo VMs in guest_memfd" for later. If this separation is acceptable, then I think I can drop the RFC tag in the next revision (I've mainly kept it here because I'm not entirely sure what to do with patches 3 and 4). === Implementation === This patch series introduces a new flag to the KVM_CREATE_GUEST_MEMFD that causes guest_memfd to remove its pages from the host kernel's direct map immediately after population/preparation. It also adds infrastructure for tracking the direct map state of all gmem folios inside the guest_memfd inode. Storing this information in the inode has the advantage that the code is ready for future hugepages extensions, where only removing/reinserting direct map entries for sub-ranges of a huge folio is a valid usecase, and it allows pre-configuring the direct map state of not-yet faulted in parts of memory (for example, when the VMM is receiving a RX virtio buffer from the guest). === Summary === Patch 1 (from Mike Rapoport) adds arch APIs for manipulating the direct map for ranges of physically contiguous pages, which are used by guest_memfd in follow up patches. Patch 2 adds the KVM_GMEM_NO_DIRECT_MAP flag and the logic for configuring direct map state of freshly prepared folios. Patches 3 and 4 mainly serve an illustrative purpose, to show how the framework from patch 2 can be extended with routines for runtime direct map manipulation. Patches 5 and 6 deal with documentation and self-tests respectively. [1]: https://download.vusec.net/papers/quarantine_raid23.pdf [RFC v1]: https://lore.kernel.org/kvm/20240709132041.3625501-1-roypat@amazon.co.uk/ [RFC v2]: https://lore.kernel.org/kvm/20240910163038.1298452-1-roypat@amazon.co.uk/ Mike Rapoport (Microsoft) (1): arch: introduce set_direct_map_valid_noflush() Patrick Roy (5): kvm: gmem: add flag to remove memory from kernel direct map kvm: gmem: implement direct map manipulation routines kvm: gmem: add trace point for direct map state changes kvm: document KVM_GMEM_NO_DIRECT_MAP flag kvm: selftests: run gmem tests with KVM_GMEM_NO_DIRECT_MAP set Documentation/virt/kvm/api.rst | 14 + arch/arm64/include/asm/set_memory.h | 1 + arch/arm64/mm/pageattr.c | 10 + arch/loongarch/include/asm/set_memory.h | 1 + arch/loongarch/mm/pageattr.c | 21 ++ arch/riscv/include/asm/set_memory.h | 1 + arch/riscv/mm/pageattr.c | 15 + arch/s390/include/asm/set_memory.h | 1 + arch/s390/mm/pageattr.c | 11 + arch/x86/include/asm/set_memory.h | 1 + arch/x86/mm/pat/set_memory.c | 8 + include/linux/set_memory.h | 6 + include/trace/events/kvm.h | 22 ++ include/uapi/linux/kvm.h | 2 + .../testing/selftests/kvm/guest_memfd_test.c | 2 +- .../kvm/x86_64/private_mem_conversions_test.c | 7 +- virt/kvm/guest_memfd.c | 280 +++++++++++++++++- 17 files changed, 384 insertions(+), 19 deletions(-) base-commit: 5cb1659f412041e4780f2e8ee49b2e03728a2ba6 -- 2.47.0

1 year

9
35
0 0

LKFT CI: improving Networking selftests results when validating stable kernels

by Matthieu Baerts

Hello LKFT maintainers, CI operators, First, I would like to say thank you to the people behind the LKFT project for validating stable kernels (and more), and including some Network selftests in their tests suites. A lot of improvements around the networking kselftests have been done this year. At the last Netconf [1], we discussed how these tests were validated on stable kernels from CIs like the LKFT one, and we have some suggestions to improve the situation. KSelftests from the same version -------------------------------- According to the doc [2], kselftests should support all previous kernel versions. The LKFT CI is then using the kselftests from the last stable release to validate all stable versions. Even if there are good reasons to do that, we would like to ask for an opt-out for this policy for the networking tests: this is hard to maintain with the increased complexity, hard to validate on all stable kernels before applying patches, and hard to put in place in some situations. As a result, many tests are failing on older kernels, and it looks like it is a lot of work to support older kernels, and to maintain this. Many networking tests are validating the internal behaviour that is not exposed to the userspace. A typical example: some tests look at the raw packets being exchanged during a test, and this behaviour can change without modifying how the userspace is interacting with the kernel. The kernel could expose capabilities, but that's not something that seems natural to put in place for internal behaviours that are not exposed to end users. Maybe workarounds could be used, e.g. looking at kernel symbols, etc. Nut that doesn't always work, increase the complexity, and often "false positive" issue will be noticed only after a patch hits stable, and will cause a bunch of tests to be ignored. Regarding fixes, ideally they will come with a new or modified test that can also be backported. So the coverage can continue to grow in stable versions too. Do you think that from the kernel v6.12 (or before?), the LKFT CI could run the networking kselftests from the version that is being validated, and not from a newer one? So validating the selftests from v6.12.1 on a v6.12.1, and not the ones from a future v6.16.y on a v6.12.42. Skipped tests ------------- It looks like many tests are skipped: - Some have been in a skip file [3] for a while: maybe they can be removed? - Some are skipped because of missing tools: maybe they can be added? e.g. iputils, tshark, ipv6toolkit, etc. - Some tests are in 'net', but in subdirectories, and hence not tested, e.g. forwarding, packetdrill, netfilter, tcp_ao. Could they be tested too? How can we change this to increase the code coverage using existing tests? KVM --- It looks like different VMs are being used to execute the different tests. Do these VMs benefit from any accelerations like KVM? If not, some tests might fail because the environment is too slow. The KSFT_MACHINE_SLOW=yes env var can be set to increase some tolerances, timeout or to skip some parts, but that might not be enough for some tests. Notifications ------------- In case of new regressions, who is being notified? Are the people from the MAINTAINERS file, and linked to the corresponding selftests being notified or do they need to do the monitoring on their side? Looking forward to improving the networking selftests results when validating stable kernels! [1] https://netdev.bots.linux.dev/netconf/2024/ [2] https://docs.kernel.org/dev-tools/kselftest.html [3] https://github.com/Linaro/test-definitions/blob/master/automated/linux/ksel… Cheers, Matt -- Sponsored by the NGI0 Core fund.

1 year

3
6
0 0

[PATCH] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

1 year

2
1
0 0

[PATCH v8 00/29] riscv control-flow integrity for usermode

by Deepak Gupta

Basics and overview =================== Software with larger attack surfaces (e.g. network facing apps like databases, browsers or apps relying on browser runtimes) suffer from memory corruption issues which can be utilized by attackers to bend control flow of the program to eventually gain control (by making their payload executable). Attackers are able to perform such attacks by leveraging call-sites which rely on indirect calls or return sites which rely on obtaining return address from stack memory. To mitigate such attacks, risc-v extension zicfilp enforces that all indirect calls must land on a landing pad instruction `lpad` else cpu will raise software check exception (a new cpu exception cause code on riscv). Similarly for return flow, risc-v extension zicfiss extends architecture with - `sspush` instruction to push return address on a shadow stack - `sspopchk` instruction to pop return address from shadow stack and compare with input operand (i.e. return address on stack) - `sspopchk` to raise software check exception if comparision above was a mismatch - Protection mechanism using which shadow stack is not writeable via regular store instructions More information an details can be found at extensions github repo [1]. Equivalent to landing pad (zicfilp) on x86 is `ENDBRANCH` instruction in Intel CET [3] and branch target identification (BTI) [4] on arm. Similarly x86's Intel CET has shadow stack [5] and arm64 has guarded control stack (GCS) [6] which are very similar to risc-v's zicfiss shadow stack. x86 already supports shadow stack for user mode and arm64 support for GCS in usermode [7] is in -next. Kernel awareness for user control flow integrity ================================================ This series picks up Samuel Holland's envcfg changes [2] as well. So if those are being applied independently, they should be removed from this series. Enabling: In order to maintain compatibility and not break anything in user mode, kernel doesn't enable control flow integrity cpu extensions on binary by default. Instead exposes a prctl interface to enable, disable and lock the shadow stack or landing pad feature for a task. This allows userspace (loader) to enumerate if all objects in its address space are compiled with shadow stack and landing pad support and accordingly enable the feature. Additionally if a subsequent `dlopen` happens on a library, user mode can take a decision again to disable the feature (if incoming library is not compiled with support) OR terminate the task (if user mode policy is strict to have all objects in address space to be compiled with control flow integirty cpu feature). prctl to enable shadow stack results in allocating shadow stack from virtual memory and activating for user address space. x86 and arm64 are also following same direction due to similar reason(s). clone/fork: On clone and fork, cfi state for task is inherited by child. Shadow stack is part of virtual memory and is a writeable memory from kernel perspective (writeable via a restricted set of instructions aka shadow stack instructions) Thus kernel changes ensure that this memory is converted into read-only when fork/clone happens and COWed when fault is taken due to sspush, sspopchk or ssamoswap. In case `CLONE_VM` is specified and shadow stack is to be enabled, kernel will automatically allocate a shadow stack for that clone call. map_shadow_stack: x86 introduced `map_shadow_stack` system call to allow user space to explicitly map shadow stack memory in its address space. It is useful to allocate shadow for different contexts managed by a single thread (green threads or contexts) risc-v implements this system call as well. signal management: If shadow stack is enabled for a task, kernel performs an asynchronous control flow diversion to deliver the signal and eventually expects userspace to issue sigreturn so that original execution can be resumed. Even though resume context is prepared by kernel, it is in user space memory and is subject to memory corruption and corruption bugs can be utilized by attacker in this race window to perform arbitrary sigreturn and eventually bypass cfi mechanism. Another issue is how to ensure that cfi related state on sigcontext area is not trampled by legacy apps or apps compiled with old kernel headers. In order to mitigate control-flow hijacting, kernel prepares a token and place it on shadow stack before signal delivery and places address of token in sigcontext structure. During sigreturn, kernel obtains address of token from sigcontext struture, reads token from shadow stack and validates it and only then allow sigreturn to succeed. Compatiblity issue is solved by adopting dynamic sigcontext management introduced for vector extension. This series re-factor the code little bit to allow future sigcontext management easy (as proposed by Andy Chiu from SiFive) config and compilation: Introduce a new risc-v config option `CONFIG_RISCV_USER_CFI`. Selecting this config option picks the kernel support for user control flow integrity. This optin is presented only if toolchain has shadow stack and landing pad support. And is on purpose guarded by toolchain support. Reason being that eventually vDSO also needs to be compiled in with shadow stack and landing pad support. vDSO compile patches are not included as of now because landing pad labeling scheme is yet to settle for usermode runtime. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` in following: Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- $ git clone git@github.com:deepak0414/qemu.git -b zicfilp_zicfiss_ratified_master_july11 $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) Branch where user cfi enabling patches are maintained https://github.com/deepak0414/linux-riscv-cfi/tree/vdso_user_cfi_v6.12-rc1 In case you're building your own rootfs using toolchain, please make sure you pick following patch to ensure that vDSO compiled with lpad and shadow stack. "arch/riscv: compile vdso with landing pad" Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. References ========== [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/all/20240814081126.956287-1-samuel.holland@sifive.c… [3] - https://lwn.net/Articles/889475/ [4] - https://developer.arm.com/documentation/109576/0100/Branch-Target-Identific… [5] - https://www.intel.com/content/dam/develop/external/us/en/documents/catc17-i… [6] - https://lwn.net/Articles/940403/ [7] - https://lore.kernel.org/all/20241001-arm64-gcs-v13-0-222b78d87eee@kernel.or… --- changelog --------- v8: - rebased on palmer/for-next - dropped samuel holland's `envcfg` context switch patches. they are in parlmer/for-next v7: - Removed "riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv" Instead using `deactivate_mm` flow to clean up. see here for more context https://lore.kernel.org/all/20230908203655.543765-1-rick.p.edgecombe@intel.… - Changed the header include in `kselftest`. Hopefully this fixes compile issue faced by Zong Li at SiFive. - Cleaned up an orphaned change to `mm/mmap.c` in below patch "riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE" - Lock interfaces for shadow stack and indirect branch tracking expect arg == 0 Any future evolution of this interface should accordingly define how arg should be setup. - `mm/map.c` has an instance of using `VM_SHADOW_STACK`. Fixed it to use helper `is_shadow_stack_vma`. - Link to v6: https://lore.kernel.org/r/20241008-v5_user_cfi_series-v6-0-60d9fe073f37@riv… v6: - Picked up Samuel Holland's changes as is with `envcfg` placed in `thread` instead of `thread_info` - fixed unaligned newline escapes in kselftest - cleaned up messages in kselftest and included test output in commit message - fixed a bug in clone path reported by Zong Li - fixed a build issue if CONFIG_RISCV_ISA_V is not selected (this was introduced due to re-factoring signal context management code) v5: - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT (https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware…) - Link to v5: https://lore.kernel.org/r/20241001-v5_user_cfi_series-v1-0-3ba65b6e550f@riv… (Note: I had an issue in my workflow due to which version number wasn't picked up correctly while sending out patches) v4: - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. - Link to v4: https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ v3: - envcfg logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. - dt-bindings As suggested, split into separate commit. fixed the messaging that spec is in public review - arch_is_shadow_stack change arch_is_shadow_stack changed to vma_is_shadow_stack - hwprobe zicfiss / zicfilp if present will get enumerated in hwprobe - selftests As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. - Link to v3: https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ v2: - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. --- Changes in v8: - EDITME: describe what is new in this series revision. - EDITME: use bulletpoints and terse descriptions. - Link to v7: https://lore.kernel.org/r/20241029-v5_user_cfi_series-v7-0-2727ce9936cb@riv… --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Clément Léger (1): riscv: Add Firmware Feature SBI extensions definitions Deepak Gupta (25): mm: helper `is_shadow_stack_vma` to check shadow stack vma dt-bindings: riscv: zicfilp and zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv mm: manufacture shadow stack pte riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs riscv mmu: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic shadow stack prctls riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception riscv/signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: kernel command line option to opt out of user cfi riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Mark Brown (2): mm: Introduce ARCH_HAS_USER_SHADOW_STACK prctl: arch-agnostic prctl for shadow stack Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 176 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 20 + arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/cpufeature.h | 13 + arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 24 + arch/riscv/include/asm/mmu_context.h | 7 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 2 + arch/riscv/include/asm/sbi.h | 27 ++ arch/riscv/include/asm/thread_info.h | 3 + arch/riscv/include/asm/usercfi.h | 89 ++++ arch/riscv/include/asm/vector.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 22 + arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/asm-offsets.c | 8 + arch/riscv/kernel/cpufeature.c | 2 + arch/riscv/kernel/entry.S | 31 +- arch/riscv/kernel/head.S | 12 + arch/riscv/kernel/process.c | 26 +- arch/riscv/kernel/ptrace.c | 83 ++++ arch/riscv/kernel/signal.c | 140 +++++- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 42 ++ arch/riscv/kernel/usercfi.c | 526 +++++++++++++++++++++ arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 17 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/cpu.h | 4 + include/linux/mm.h | 5 +- include/uapi/asm-generic/mman.h | 4 + include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 48 ++ kernel/sys.c | 60 +++ mm/Kconfig | 6 + mm/gup.c | 2 +- mm/mmap.c | 2 +- mm/vma.h | 10 +- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 84 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 78 +++ tools/testing/selftests/riscv/cfi/shadowstack.c | 373 +++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 ++ 54 files changed, 2171 insertions(+), 35 deletions(-) --- base-commit: 64f7b77f0bd9271861ed9e410e9856b6b0b21c48 change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

1 year

2
36
0 0

[PATCH net 2/2] selftests: net: test extacks in netlink dumps

by Jakub Kicinski

Test that extacks in dumps work. The test fills up the receive buffer to test both the inline dump (as part of sendmsg()) and delayed one (run during recvmsg()). Use YNL helpers to parse the messages. We need to add the test to YNL file to make sure the right include path are used. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/netlink-dumps.c | 129 ++++++++++++++++++++ 2 files changed, 130 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5e86f7a51b43..c427ee32b193 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -78,7 +78,6 @@ TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash -TEST_GEN_PROGS += netlink-dumps TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_GEN_PROGS += sk_so_peek_off @@ -100,7 +99,7 @@ TEST_PROGS += bpf_offload.py # YNL files, must be before "include ..lib.mk" EXTRA_CLEAN += $(OUTPUT)/libynl.a -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := ncdevmem netlink-dumps TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_FILES := settings diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7ee6dcd334df..195febbf6a61 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -12,11 +12,140 @@ #include <unistd.h> #include <linux/genetlink.h> +#include <linux/neighbour.h> +#include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/mqueue.h> +#include <linux/rtnetlink.h> #include "../kselftest_harness.h" +#include <ynl.h> + +struct ext_ack { + int err; + + __u32 attr_offs; + __u32 miss_type; + __u32 miss_nest; + const char *str; +}; + +/* 0: no done, 1: done found, 2: extack found, -1: error */ +static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) +{ + const struct nlmsghdr *nlh; + const struct nlattr *attr; + ssize_t rem; + + for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) { + nlh = (struct nlmsghdr *)&buf[n - rem]; + if (!NLMSG_OK(nlh, rem)) + return -1; + + if (nlh->nlmsg_type != NLMSG_DONE) + continue; + + ea->err = -*(int *)NLMSG_DATA(nlh); + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 1; + + ynl_attr_for_each(attr, nlh, sizeof(int)) { + switch (ynl_attr_type(attr)) { + case NLMSGERR_ATTR_OFFS: + ea->attr_offs = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_TYPE: + ea->miss_type = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_NEST: + ea->miss_nest = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MSG: + ea->str = ynl_attr_get_str(attr); + break; + } + } + + return 2; + } + + return 0; +} + +static const struct { + struct nlmsghdr nlhdr; + struct ndmsg ndm; + struct nlattr ahdr; + __u32 val; +} dump_neigh_bad = { + .nlhdr = { + .nlmsg_len = sizeof(dump_neigh_bad), + .nlmsg_type = RTM_GETNEIGH, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + .nlmsg_seq = 1, + }, + .ndm = { + .ndm_family = 123, + }, + .ahdr = { + .nla_len = 4 + 4, + .nla_type = NDA_FLAGS_EXT, + }, + .val = -1, // should fail MASK validation +}; + +TEST(dump_extack) +{ + int netlink_sock; + char buf[8192]; + int one = 1; + int i, cnt; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + ASSERT_GE(netlink_sock, 0); + + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_CAP_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_GET_STRICT_CHK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + + /* Dump so many times we fill up the buffer */ + cnt = 64; + for (i = 0; i < cnt; i++) { + n = send(netlink_sock, &dump_neigh_bad, + sizeof(dump_neigh_bad), 0); + ASSERT_EQ(n, sizeof(dump_neigh_bad)); + } + + /* Read out the ENOBUFS */ + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + EXPECT_EQ(n, -1); + EXPECT_EQ(errno, ENOBUFS); + + for (i = 0; i < cnt; i++) { + struct ext_ack ea = {}; + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + if (n < 0) { + ASSERT_GE(i, 10); + break; + } + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); + + EXPECT_EQ(nl_get_extack(buf, n, &ea), 2); + EXPECT_EQ(ea.attr_offs, + sizeof(struct nlmsghdr) + sizeof(struct ndmsg)); + } +} + static const struct { struct nlmsghdr nlhdr; struct genlmsghdr genlhdr; -- 2.47.0

1 year

1
0
0 0

[PATCH net-next v4 7/7] selftests: net: fdb_notify: Add a test for FDB notifications

by Petr Machata

Check that only one notification is produced for various FDB edit operations. Regarding the ip_link_add() and ip_link_master() helpers. This pattern of action plus corresponding defer is bound to come up often, and a dedicated vocabulary to capture it will be handy. tunnel_create() and vlan_create() from forwarding/lib.sh are somewhat opaque and perhaps too kitchen-sinky, so I tried to go in the opposite direction with these ones, and wrapped only the bare minimum to schedule a corresponding cleanup. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: v4: - Adjust the sleep around the FDB op --- CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/fdb_notify.sh | 96 +++++++++++++++++++++++ tools/testing/selftests/net/lib.sh | 17 ++++ 3 files changed, 114 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/fdb_notify.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 2b2a5ec7fa6a..d1494700f501 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -92,7 +92,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh -TEST_PROGS += fdb_flush.sh +TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh new file mode 100755 index 000000000000..c03151e7791c --- /dev/null +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +ALL_TESTS=" + test_dup_bridge + test_dup_vxlan_self + test_dup_vxlan_master + test_dup_macvlan_self + test_dup_macvlan_master +" + +do_test_dup() +{ + local op=$1; shift + local what=$1; shift + local tmpf + + RET=0 + + tmpf=$(mktemp) + defer rm "$tmpf" + + defer_scope_push + bridge monitor fdb &> "$tmpf" & + defer kill_process $! + + sleep 0.5 + bridge fdb "$op" 00:11:22:33:44:55 vlan 1 "$@" + sleep 0.5 + defer_scope_pop + + local count=$(grep -c -e 00:11:22:33:44:55 $tmpf) + ((count == 1)) + check_err $? "Got $count notifications, expected 1" + + log_test "$what $op: Duplicate notifications" +} + +test_dup_bridge() +{ + ip_link_add br up type bridge vlan_filtering 1 + do_test_dup add "bridge" dev br self + do_test_dup del "bridge" dev br self +} + +test_dup_vxlan_self() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan" dev vx self dst 192.0.2.1 + do_test_dup del "vxlan" dev vx self dst 192.0.2.1 +} + +test_dup_vxlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan master" dev vx master + do_test_dup del "vxlan master" dev vx master +} + +test_dup_macvlan_self() +{ + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + + do_test_dup add "macvlan self" dev mv self + do_test_dup del "macvlan self" dev mv self +} + +test_dup_macvlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + ip_link_master mv br + + do_test_dup add "macvlan master" dev mv self + do_test_dup del "macvlan master" dev mv self +} + +cleanup() +{ + defer_scopes_cleanup +} + +trap cleanup EXIT +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 24f63e45735d..8994fec1c38f 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -442,3 +442,20 @@ kill_process() # Suppress noise from killing the process. { kill $pid && wait $pid; } 2>/dev/null } + +ip_link_add() +{ + local name=$1; shift + + ip link add name "$name" "$@" + defer ip link del dev "$name" +} + +ip_link_master() +{ + local member=$1; shift + local master=$1; shift + + ip link set dev "$member" master "$master" + defer ip link set dev "$member" nomaster +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v4 6/7] selftests: net: lib: Add kill_process

by Petr Machata

A number of selftests run processes in the background and need to kill them afterwards. Instead for everyone to open-code the kill / wait / redirect mantra, add a helper in net/lib.sh. Convert existing open-code sites. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> CC: Andrew Lunn <andrew+netdev(a)lunn.ch> .../selftests/drivers/net/mlxsw/devlink_trap.sh | 2 +- .../drivers/net/mlxsw/devlink_trap_l3_drops.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_l3_exceptions.sh | 12 ++++++------ .../drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh | 4 ++-- .../net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh | 4 ++-- .../testing/selftests/drivers/net/mlxsw/tc_sample.sh | 4 ++-- .../drivers/net/netdevsim/fib_notifications.sh | 6 +++--- tools/testing/selftests/net/drop_monitor_tests.sh | 2 +- tools/testing/selftests/net/fib_tests.sh | 8 ++++---- .../testing/selftests/net/forwarding/devlink_lib.sh | 2 +- tools/testing/selftests/net/forwarding/lib.sh | 3 +-- tools/testing/selftests/net/forwarding/tc_police.sh | 8 ++++---- tools/testing/selftests/net/lib.sh | 8 ++++++++ 15 files changed, 41 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh index 89b55e946eed..36055279ba92 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh @@ -116,7 +116,7 @@ dev_del_test() log_test "Device delete" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index 160891dcb4bc..db5806d189bb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -595,7 +595,7 @@ irif_disabled_test() log_test "Ingress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip link set dev $rp1 nomaster __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge @@ -645,7 +645,7 @@ erif_disabled_test() log_test "Egress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge devlink_trap_action_set $trap_name "drop" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh index 190c1b6b5365..5d6d88b600f0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh @@ -202,7 +202,7 @@ mtu_value_is_too_small_test() mtu_restore $rp2 - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -235,7 +235,7 @@ __ttl_value_is_too_small_test() log_test "TTL value is too small: TTL=$ttl_val" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -299,7 +299,7 @@ __mc_reverse_path_forwarding_test() log_test "Multicast reverse path forwarding: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower } @@ -347,7 +347,7 @@ __reject_route_test() log_test "Reject route: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip route del unreachable $unreachable tc filter del dev $h1 ingress protocol $proto pref 1 handle 101 flower } @@ -542,7 +542,7 @@ ipv4_lpm_miss_test() log_test "LPM miss: IPv4" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } @@ -569,7 +569,7 @@ ipv6_lpm_miss_test() log_test "LPM miss: IPv6" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index e9a82cae8c9a..4ac1dae92d0f 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh index 878125041fc3..fce885184404 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index 5f6eb965cfd1..7aca8e5922cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -183,7 +183,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -253,7 +253,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh index f6c16cbb6cf7..4599c331240b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh @@ -188,7 +188,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -262,7 +262,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 83a0210e7544..bc7ea2df49fb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -218,7 +218,7 @@ psample_capture_start() psample_capture_stop() { - { kill %% && wait %%; } 2>/dev/null + kill_process %% } __tc_sample_rate_test() @@ -499,7 +499,7 @@ tc_sample_md_out_tc_occ_test() backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]') # Kill mausezahn. - { kill %% && wait %%; } 2>/dev/null + kill_process %% psample_capture_stop diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh index 8d91191a098c..9896580c3d85 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh @@ -94,7 +94,7 @@ route_addition_check() sleep 1 $IP route add $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications $offload_failed rm -f $outfile @@ -148,7 +148,7 @@ route_deletion_check() sleep 1 $IP route del $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile @@ -191,7 +191,7 @@ route_replacement_check() sleep 1 $IP route replace $route dev dummy2 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh index 7c4818c971fc..507d0a82f5f0 100755 --- a/tools/testing/selftests/net/drop_monitor_tests.sh +++ b/tools/testing/selftests/net/drop_monitor_tests.sh @@ -77,7 +77,7 @@ sw_drops_test() rm ${dir}/packets.pcap - { kill %% && wait %%; } 2>/dev/null + kill_process %% timeout 5 dwdump -o sw -w ${dir}/packets.pcap (( $(tshark -r ${dir}/packets.pcap \ -Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) == 0)) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5f3c28fc8624..3ea6f886a210 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -689,7 +689,7 @@ fib6_notify_test() log_test $ret 0 "ipv6 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% #rm errors.txt @@ -736,7 +736,7 @@ fib_notify_test() log_test $ret 0 "ipv4 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm errors.txt @@ -2328,7 +2328,7 @@ ipv4_mangle_test() $IP route del table 123 172.16.101.0/24 dev veth1 $IP rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup @@ -2386,7 +2386,7 @@ ipv6_mangle_test() $IP -6 route del table 123 2001:db8:101::/64 dev veth1 $IP -6 rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 62a05bca1e82..18afa89ebbcc 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -501,7 +501,7 @@ devlink_trap_drop_cleanup() local pref=$1; shift local handle=$1; shift - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8625e3c99f55..7337f398f9cc 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1574,8 +1574,7 @@ stop_traffic() { local pid=${1-%%}; shift - # Suppress noise from killing mausezahn. - { kill $pid && wait $pid; } 2>/dev/null + kill_process "$pid" } declare -A cappid diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 5103f64a71d6..509fdedfcfa1 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -148,7 +148,7 @@ police_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } @@ -198,7 +198,7 @@ police_shared_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% } police_shared_test() @@ -278,7 +278,7 @@ police_mirror_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower @@ -320,7 +320,7 @@ police_pps_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 6bcf5d13879d..24f63e45735d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -434,3 +434,11 @@ xfail_on_veth() "$@" fi } + +kill_process() +{ + local pid=$1; shift + + # Suppress noise from killing the process. + { kill $pid && wait $pid; } 2>/dev/null +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v4 5/7] selftests: net: lib: Move checks from forwarding/lib.sh here

by Petr Machata

For logging to be useful, something has to set RET and retmsg by calling ret_set_ksft_status(). There is a suite of functions to that end in forwarding/lib: check_err, check_fail et.al. Move them to net/lib.sh so that every net test can use them. Existing lib.sh users might be using these same names for their functions. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 73 ------------------- tools/testing/selftests/net/lib.sh | 73 +++++++++++++++++++ 2 files changed, 73 insertions(+), 73 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index d28dbf27c1f0..8625e3c99f55 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -445,79 +445,6 @@ done ############################################################################## # Helpers -# Whether FAILs should be interpreted as XFAILs. Internal. -FAIL_TO_XFAIL= - -check_err() -{ - local err=$1 - local msg=$2 - - if ((err)); then - if [[ $FAIL_TO_XFAIL = yes ]]; then - ret_set_ksft_status $ksft_xfail "$msg" - else - ret_set_ksft_status $ksft_fail "$msg" - fi - fi -} - -check_fail() -{ - local err=$1 - local msg=$2 - - check_err $((!err)) "$msg" -} - -check_err_fail() -{ - local should_fail=$1; shift - local err=$1; shift - local what=$1; shift - - if ((should_fail)); then - check_fail $err "$what succeeded, but should have failed" - else - check_err $err "$what failed" - fi -} - -xfail() -{ - FAIL_TO_XFAIL=yes "$@" -} - -xfail_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW = yes ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - -omit_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW != yes ]]; then - "$@" - fi -} - -xfail_on_veth() -{ - local dev=$1; shift - local kind - - kind=$(ip -j -d link show dev $dev | - jq -r '.[].linkinfo.info_kind') - if [[ $kind = veth ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 4f52b8e48a3a..6bcf5d13879d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -361,3 +361,76 @@ tests_run() $current_test done } + +# Whether FAILs should be interpreted as XFAILs. Internal. +FAIL_TO_XFAIL= + +check_err() +{ + local err=$1 + local msg=$2 + + if ((err)); then + if [[ $FAIL_TO_XFAIL = yes ]]; then + ret_set_ksft_status $ksft_xfail "$msg" + else + ret_set_ksft_status $ksft_fail "$msg" + fi + fi +} + +check_fail() +{ + local err=$1 + local msg=$2 + + check_err $((!err)) "$msg" +} + +check_err_fail() +{ + local should_fail=$1; shift + local err=$1; shift + local what=$1; shift + + if ((should_fail)); then + check_fail $err "$what succeeded, but should have failed" + else + check_err $err "$what failed" + fi +} + +xfail() +{ + FAIL_TO_XFAIL=yes "$@" +} + +xfail_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW = yes ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} + +omit_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW != yes ]]; then + "$@" + fi +} + +xfail_on_veth() +{ + local dev=$1; shift + local kind + + kind=$(ip -j -d link show dev $dev | + jq -r '.[].linkinfo.info_kind') + if [[ $kind = veth ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v4 4/7] selftests: net: lib: Move tests_run from forwarding/lib.sh here

by Petr Machata

It would be good to use the same mechanism for scheduling and dispatching general net tests as the many forwarding tests already use. To that end, move the logging helpers to net/lib.sh so that every net test can use them. Existing lib.sh users might be using the name themselves. However lib.sh is always sourced near the top of the file (checked), and whatever new definition will simply override the one provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 10 ---------- tools/testing/selftests/net/lib.sh | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 41dd14c42c48..d28dbf27c1f0 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1285,16 +1285,6 @@ matchall_sink_create() action drop } -tests_run() -{ - local current_test - - for current_test in ${TESTS:-$ALL_TESTS}; do - in_defer_scope \ - $current_test - done -} - cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 691318b1ec55..4f52b8e48a3a 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -351,3 +351,13 @@ log_info() echo "INFO: $msg" } + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + in_defer_scope \ + $current_test + done +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v4 3/7] selftests: net: lib: Move logging from forwarding/lib.sh here

by Petr Machata

Many net selftests invent their own logging helpers. These really should be in a library sourced by these tests. Currently forwarding/lib.sh has a suite of perfectly fine logging helpers, but sourcing a forwarding/ library from a higher-level directory smells of layering violation. In this patch, move the logging helpers to net/lib.sh so that every net test can use them. Together with the logging helpers, it's also necessary to move pause_on_fail(), and EXIT_STATUS and RET. Existing lib.sh users might be using these same names for their functions or variables. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 113 ----------------- tools/testing/selftests/net/lib.sh | 115 ++++++++++++++++++ 2 files changed, 115 insertions(+), 113 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 89c25f72b10c..41dd14c42c48 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -48,7 +48,6 @@ declare -A NETIFS=( : "${WAIT_TIME:=5}" # Whether to pause on, respectively, after a failure and before cleanup. -: "${PAUSE_ON_FAIL:=no}" : "${PAUSE_ON_CLEANUP:=no}" # Whether to create virtual interfaces, and what netdevice type they should be. @@ -446,22 +445,6 @@ done ############################################################################## # Helpers -# Exit status to return at the end. Set in case one of the tests fails. -EXIT_STATUS=0 -# Per-test return value. Clear at the beginning of each test. -RET=0 - -ret_set_ksft_status() -{ - local ksft_status=$1; shift - local msg=$1; shift - - RET=$(ksft_status_merge $RET $ksft_status) - if (( $? )); then - retmsg=$msg - fi -} - # Whether FAILs should be interpreted as XFAILs. Internal. FAIL_TO_XFAIL= @@ -535,102 +518,6 @@ xfail_on_veth() fi } -log_test_result() -{ - local test_name=$1; shift - local opt_str=$1; shift - local result=$1; shift - local retmsg=$1; shift - - printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" - if [[ $retmsg ]]; then - printf "\t%s\n" "$retmsg" - fi -} - -pause_on_fail() -{ - if [[ $PAUSE_ON_FAIL == yes ]]; then - echo "Hit enter to continue, 'q' to quit" - read a - [[ $a == q ]] && exit 1 - fi -} - -handle_test_result_pass() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" " OK " -} - -handle_test_result_fail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" FAIL "$retmsg" - pause_on_fail -} - -handle_test_result_xfail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" - pause_on_fail -} - -handle_test_result_skip() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" SKIP "$retmsg" -} - -log_test() -{ - local test_name=$1 - local opt_str=$2 - - if [[ $# -eq 2 ]]; then - opt_str="($opt_str)" - fi - - if ((RET == ksft_pass)); then - handle_test_result_pass "$test_name" "$opt_str" - elif ((RET == ksft_xfail)); then - handle_test_result_xfail "$test_name" "$opt_str" - elif ((RET == ksft_skip)); then - handle_test_result_skip "$test_name" "$opt_str" - else - handle_test_result_fail "$test_name" "$opt_str" - fi - - EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) - return $RET -} - -log_test_skip() -{ - RET=$ksft_skip retmsg= log_test "$@" -} - -log_test_xfail() -{ - RET=$ksft_xfail retmsg= log_test "$@" -} - -log_info() -{ - local msg=$1 - - echo "INFO: $msg" -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index c8991cc6bf28..691318b1ec55 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -9,6 +9,9 @@ source "$net_dir/lib/sh/defer.sh" : "${WAIT_TIMEOUT:=20}" +# Whether to pause on after a failure. +: "${PAUSE_ON_FAIL:=no}" + BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms # Kselftest framework constants. @@ -20,6 +23,11 @@ ksft_skip=4 # namespace list created by setup_ns NS_LIST=() +# Exit status to return at the end. Set in case one of the tests fails. +EXIT_STATUS=0 +# Per-test return value. Clear at the beginning of each test. +RET=0 + ############################################################################## # Helpers @@ -236,3 +244,110 @@ tc_rule_handle_stats_get() | jq ".[] | select(.options.handle == $handle) | \ .options.actions[0].stats$selector" } + +ret_set_ksft_status() +{ + local ksft_status=$1; shift + local msg=$1; shift + + RET=$(ksft_status_merge $RET $ksft_status) + if (( $? )); then + retmsg=$msg + fi +} + +log_test_result() +{ + local test_name=$1; shift + local opt_str=$1; shift + local result=$1; shift + local retmsg=$1; shift + + printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" + if [[ $retmsg ]]; then + printf "\t%s\n" "$retmsg" + fi +} + +pause_on_fail() +{ + if [[ $PAUSE_ON_FAIL == yes ]]; then + echo "Hit enter to continue, 'q' to quit" + read a + [[ $a == q ]] && exit 1 + fi +} + +handle_test_result_pass() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" " OK " +} + +handle_test_result_fail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" FAIL "$retmsg" + pause_on_fail +} + +handle_test_result_xfail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" + pause_on_fail +} + +handle_test_result_skip() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" SKIP "$retmsg" +} + +log_test() +{ + local test_name=$1 + local opt_str=$2 + + if [[ $# -eq 2 ]]; then + opt_str="($opt_str)" + fi + + if ((RET == ksft_pass)); then + handle_test_result_pass "$test_name" "$opt_str" + elif ((RET == ksft_xfail)); then + handle_test_result_xfail "$test_name" "$opt_str" + elif ((RET == ksft_skip)); then + handle_test_result_skip "$test_name" "$opt_str" + else + handle_test_result_fail "$test_name" "$opt_str" + fi + + EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) + return $RET +} + +log_test_skip() +{ + RET=$ksft_skip retmsg= log_test "$@" +} + +log_test_xfail() +{ + RET=$ksft_xfail retmsg= log_test "$@" +} + +log_info() +{ + local msg=$1 + + echo "INFO: $msg" +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v1 08/10] mm: page_frag: add testing for the newly added API

by Yunsheng Lin

Add testing for the newly added prepare API, for both aligned and non-aligned API, also probe API is also tested along with prepare API. CC: Alexander Duyck <alexander.duyck(a)gmail.com> CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Linux-MM <linux-mm(a)kvack.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- .../selftests/mm/page_frag/page_frag_test.c | 76 +++++++++++++++++-- tools/testing/selftests/mm/run_vmtests.sh | 4 + tools/testing/selftests/mm/test_page_frag.sh | 27 +++++++ 3 files changed, 102 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index e806c1866e36..3b3c32389def 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -32,6 +32,10 @@ static bool test_align; module_param(test_align, bool, 0); MODULE_PARM_DESC(test_align, "use align API for testing"); +static bool test_prepare; +module_param(test_prepare, bool, 0); +MODULE_PARM_DESC(test_prepare, "use prepare API for testing"); + static int test_alloc_len = 2048; module_param(test_alloc_len, int, 0); MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); @@ -74,6 +78,21 @@ static int page_frag_pop_thread(void *arg) return 0; } +static void frag_frag_test_commit(struct page_frag_cache *nc, + struct page_frag *prepare_pfrag, + struct page_frag *probe_pfrag, + unsigned int used_sz) +{ + if (prepare_pfrag->page != probe_pfrag->page || + prepare_pfrag->offset != probe_pfrag->offset || + prepare_pfrag->size != probe_pfrag->size) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong probed info\n"); + } + + page_frag_refill_commit(nc, prepare_pfrag, used_sz); +} + static int page_frag_push_thread(void *arg) { struct ptr_ring *ring = arg; @@ -86,15 +105,61 @@ static int page_frag_push_thread(void *arg) int ret; if (test_align) { - va = page_frag_alloc_align(&test_nc, test_alloc_len, - GFP_KERNEL, SMP_CACHE_BYTES); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare_align(&test_nc, + test_alloc_len, + &prepare_frag, + GFP_KERNEL, + SMP_CACHE_BYTES); + + probe_va = __page_frag_alloc_refill_probe_align(&test_nc, + test_alloc_len, + &probe_frag, + -SMP_CACHE_BYTES); + if (va != probe_va) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n"); + } + + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc_align(&test_nc, + test_alloc_len, + GFP_KERNEL, + SMP_CACHE_BYTES); + } if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { force_exit = true; WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); } } else { - va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare(&test_nc, test_alloc_len, + &prepare_frag, GFP_KERNEL); + + probe_va = page_frag_alloc_refill_probe(&test_nc, test_alloc_len, + &probe_frag); + + if (va != probe_va) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n"); + } + + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } } if (!va) @@ -176,8 +241,9 @@ static int __init page_frag_test_init(void) } duration = (u64)ktime_us_delta(ktime_get(), start); - pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, - test_align ? "aligned" : "non-aligned", duration); + pr_info("%d of iterations for %s %s API testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", + test_prepare ? "prepare" : "alloc", duration); out: ptr_ring_cleanup(&ptr_ring, NULL); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2c5394584af4..f6ff9080a6f2 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -464,6 +464,10 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned_prepare + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned_prepare + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh index f55b105084cf..1c757fd11844 100755 --- a/tools/testing/selftests/mm/test_page_frag.sh +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -43,6 +43,8 @@ check_test_failed_prefix() { SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" +NONALIGNED_PREPARE_PARAM="$NONALIGNED_PARAM test_prepare=1" +ALIGNED_PREPARE_PARAM="$ALIGNED_PARAM test_prepare=1" check_test_requirements() { @@ -77,6 +79,20 @@ run_aligned_check() insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 } +run_nonaligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast nonaligned prepare API is." + + insmod $DRIVER $NONALIGNED_PREPARE_PARAM > /dev/null 2>&1 +} + +run_aligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast aligned prepare API is." + + insmod $DRIVER $ALIGNED_PREPARE_PARAM > /dev/null 2>&1 +} + run_smoke_check() { echo "Run smoke test." @@ -87,6 +103,7 @@ run_smoke_check() usage() { echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "[ aligned_prepare ] | [ nonaligned_prepare ] | " echo "manual parameters" echo echo "Valid tests and parameters:" @@ -107,6 +124,12 @@ usage() echo "# Performance testing for aligned alloc API" echo "$0 aligned" echo + echo "# Performance testing for nonaligned prepare API" + echo "$0 nonaligned_prepare" + echo + echo "# Performance testing for aligned prepare API" + echo "$0 aligned_prepare" + echo exit 0 } @@ -158,6 +181,10 @@ function run_test() run_nonaligned_check elif [[ "$1" = "aligned" ]]; then run_aligned_check + elif [[ "$1" = "nonaligned_prepare" ]]; then + run_nonaligned_prepare_check + elif [[ "$1" = "aligned_prepare" ]]; then + run_aligned_prepare_check else run_manual_check $@ fi -- 2.33.0

1 year

1
0
0 0

[PATCH] net/unix: pass pidfd flags via SCM_PIDFD cmsg

by Stas Sergeev

Currently SCM_PIDFD cmsg cannot be sent via unix socket (returns -EINVAL) and SO_PASSPIDFD doesn't support flags. The created pidfd always has flags set to 0. This patch implements SCM_PIDFD cmsg in AF_UNIX socket, which can be used to send flags to SO_PASSPIDFD-enabled recipient. Self-test is added for the propagation of PIDFD_NONBLOCK flag. This is mainly needed for the future extensions, like eg this one: https://lore.kernel.org/lkml/8288a08e-448b-43c2-82dc-59f87d0d9072@yandex.ru… where it was suggested to try solving the supplementary groups problem with pidfd. Signed-off-by: Stas Sergeev <stsp2(a)yandex.ru> 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: Simon Horman <horms(a)kernel.org> CC: Shuah Khan <shuah(a)kernel.org> CC: Christian Brauner <brauner(a)kernel.org> CC: Jens Axboe <axboe(a)kernel.dk> CC: Willem de Bruijn <willemb(a)google.com> CC: Pavel Begunkov <asml.silence(a)gmail.com> CC: Gabriel Krisman Bertazi <krisman(a)suse.de> CC: Mina Almasry <almasrymina(a)google.com> CC: Oleg Nesterov <oleg(a)redhat.com> CC: Tycho Andersen <tandersen(a)netflix.com> CC: Al Viro <viro(a)zeniv.linux.org.uk> CC: Kuniyuki Iwashima <kuniyu(a)amazon.com> CC: Gou Hao <gouhao(a)uniontech.com> CC: Abhishek Chauhan <quic_abchauha(a)quicinc.com> CC: Michal Luczaj <mhal(a)rbox.co> CC: Kees Cook <kees(a)kernel.org> CC: linux-kernel(a)vger.kernel.org CC: netdev(a)vger.kernel.org CC: linux-kselftest(a)vger.kernel.org --- include/linux/pidfs.h | 9 +++ include/linux/socket.h | 2 +- include/net/af_unix.h | 1 + include/net/scm.h | 10 ++- kernel/pid.c | 6 +- net/core/scm.c | 14 ++++ net/core/sock.c | 1 + net/unix/af_unix.c | 3 + .../testing/selftests/net/af_unix/scm_pidfd.c | 70 +++++++++++++++++-- 9 files changed, 106 insertions(+), 10 deletions(-) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..c4c5c1a0c2ad 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,7 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +#include <uapi/linux/pidfd.h> + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +static inline int pidfd_validate_flags(unsigned int flags) +{ + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) + return -EINVAL; + return 0; +} + #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..ee27d391e5aa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -178,7 +178,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD 0x04 /* r: pidfd, w: pidfd_flags (int) */ struct ucred { __u32 pid; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 63129c79b8cb..4bc197548c2f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_skb_parms { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif + u32 pidfd_flags; u32 consumed; } __randomize_layout; diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..bc64d516b226 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -8,6 +8,7 @@ #include <linux/file.h> #include <linux/security.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/sched/signal.h> #include <net/compat.h> @@ -48,6 +49,7 @@ struct scm_cookie { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Passed security ID */ #endif + u32 pidfd_flags; }; void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); @@ -137,6 +139,7 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm { struct file *pidfd_file = NULL; int len, pidfd; + int err; /* put_cmsg() doesn't return an error if CMSG is truncated, * that's why we need to opencode these checks here. @@ -154,7 +157,12 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm if (!scm->pid) return; - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + err = pidfd_validate_flags(scm->pidfd_flags); + if (err) { + msg->msg_flags |= MSG_CTRUNC; + return; + } + pidfd = pidfd_prepare(scm->pid, scm->pidfd_flags, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..b1100ae8ea63 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -629,10 +629,12 @@ static int pidfd_create(struct pid *pid, unsigned int flags) SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; + int err; struct pid *p; - if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) - return -EINVAL; + err = pidfd_validate_flags(flags); + if (err) + return err; if (pid <= 0) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..3bcdecdacd7e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -23,6 +23,7 @@ #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> @@ -210,6 +211,19 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->creds.gid = gid; break; } + case SCM_PIDFD: + { + unsigned int flags; + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(flags))) + goto error; + memcpy(&flags, CMSG_DATA(cmsg), sizeof(flags)); + err = pidfd_validate_flags(flags); + if (err) + goto error; + p->pidfd_flags = flags; + break; + } default: goto error; } diff --git a/net/core/sock.c b/net/core/sock.c index 039be95c40cf..d1fce437c035 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2930,6 +2930,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: + case SCM_PIDFD: break; default: return -EINVAL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..8b19dfec0221 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1892,6 +1892,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; + UNIXCB(skb).pidfd_flags = scm->pidfd_flags; unix_get_secdata(scm, skb); if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -2486,6 +2487,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); if (!(flags & MSG_PEEK)) { @@ -2873,6 +2875,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); check_creds = true; } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..1e70ff253a1d 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -5,6 +5,7 @@ #include <stddef.h> #include <stdio.h> #include <stdlib.h> +#include <fcntl.h> #include <sys/socket.h> #include <linux/socket.h> #include <unistd.h> @@ -15,6 +16,11 @@ #include <sys/types.h> #include <sys/wait.h> +/* There are problems including linux/pidfd.h, so define. */ +#ifndef PIDFD_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#endif + #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -126,7 +132,7 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } -static int cmsg_check(int fd) +static int cmsg_check(int fd, unsigned int pidfd_flags) { struct msghdr msg = { 0 }; struct cmsghdr *cmsg; @@ -136,6 +142,7 @@ static int cmsg_check(int fd) char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; int *pidfd = NULL; + unsigned int flags; pid_t parent_pid; int err; @@ -197,6 +204,13 @@ static int cmsg_check(int fd) return 1; } + flags = fcntl(*pidfd, F_GETFL, 0); + flags &= ~O_ACCMODE; + if (flags != pidfd_flags) { + log_err("SCM_PIDFD flags mismatch: %x != %x", flags, pidfd_flags); + 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); @@ -227,30 +241,49 @@ FIXTURE_VARIANT(scm_pidfd) { int type; bool abstract; + unsigned int flags; }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) { .type = SOCK_STREAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) { .type = SOCK_STREAM, .abstract = 1, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) { .type = SOCK_DGRAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) { .type = SOCK_DGRAM, .abstract = 1, + .flags = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_nonblock) +{ + .type = SOCK_STREAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_nonblock) +{ + .type = SOCK_DGRAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, }; FIXTURE_SETUP(scm_pidfd) @@ -335,7 +368,7 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, close(self->startup_pipe[1]); - if (cmsg_check(cfd)) { + if (cmsg_check(cfd, variant->flags)) { log_err("cmsg_check failed"); child_die(); } @@ -375,6 +408,27 @@ TEST_F(scm_pidfd, test) int err; int pfd; int child_status = 0; + char iobuf; + unsigned int pidfd_flags; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec io = { + .iov_base = &iobuf, + .iov_len = sizeof(iobuf) + }; + union { + char buf[CMSG_SPACE(sizeof(pidfd_flags))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_PIDFD; + cmsg->cmsg_len = CMSG_LEN(sizeof(pidfd_flags)); self->server = socket(AF_UNIX, variant->type, 0); ASSERT_NE(-1, self->server); @@ -414,12 +468,16 @@ TEST_F(scm_pidfd, test) 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); + err = connect(pfd, + (struct sockaddr *)&self->client_addr->listen_addr, + self->client_addr->addrlen); ASSERT_NE(-1, err); } + iobuf = 'x'; + pidfd_flags = variant->flags; + memcpy(CMSG_DATA(cmsg), &pidfd_flags, sizeof(pidfd_flags)); + err = sendmsg(pfd, &msg, 0); + ASSERT_NE(-1, err); close(pfd); waitpid(self->client_pid, &child_status, 0); -- 2.47.0

1 year

3
2
0 0

[PATCH bpf-next 00/10] selftests/bpf: migrate test_flow_dissector.sh to test_progs

by Alexis Lothoré (eBPF Foundation)

Hello, this new series aims to migrate test_flow_dissector.sh into test_progs. There are 2 "main" parts in test_flow_dissector.sh: - a set of tests checking flow_dissector programs attachment to either root namespace or non-root namespace - dissection test The first set is integrated in flow_dissector.c, which already contains some existing tests for flow_dissector programs. This series uses the opportunity to update a bit this file (use new assert, re-split tests, etc) The second part is migrated into a new file under test_progs, flow_dissector_classification.c. It uses the same eBPF programs as flow_dissector.c, but the difference is rather about how those program are executed: - flow_dissector.c manually runs programs with BPF_PROG_RUN - flow_dissector_classification.c sends real packets to be dissected, and so it also executes kernel code related to eBPF flow dissector (eg: __skb_flow_bpf_to_target) --- Alexis Lothoré (eBPF Foundation) (10): selftests/bpf: add a macro to compare raw memory selftests/bpf: use ASSERT_MEMEQ to compare bpf flow keys selftests/bpf: replace CHECK calls with ASSERT macros in flow_dissector test selftests/bpf: re-split main function into dedicated tests selftests/bpf: expose all subtests from flow_dissector selftests/bpf: add gre packets testing to flow_dissector selftests/bpf: migrate flow_dissector namespace exclusivity test selftests/bpf: Enable generic tc actions in selftests config selftests/bpf: migrate bpf flow dissectors tests to test_progs selftests/bpf: remove test_flow_dissector.sh tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/config | 1 + .../selftests/bpf/prog_tests/flow_dissector.c | 307 ++++++-- .../bpf/prog_tests/flow_dissector_classification.c | 851 +++++++++++++++++++++ tools/testing/selftests/bpf/test_flow_dissector.c | 780 ------------------- tools/testing/selftests/bpf/test_flow_dissector.sh | 178 ----- tools/testing/selftests/bpf/test_progs.h | 25 + 8 files changed, 1107 insertions(+), 1039 deletions(-) --- base-commit: 16e1d1c377aa4c56223701a31f3bfa88505e7e4f change-id: 20241019-flow_dissector-3eb0c07fc163 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

1 year

3
24
0 0

[PATCH v2 1/2] kunit: tool: Only print the summary

by Rae Moar

From: David Gow <davidgow(a)google.com> Allow only printing the summary at the end of a test run, rather than all individual test results. This summary will list a few failing tests if there are any. To use: ./tools/testing/kunit/kunit.py run --summary Signed-off-by: Rae Moar <rmoar(a)google.com> Signed-off-by: David Gow <davidgow(a)google.com> --- Changes since v1: - kunit_printer init changed to include print variable to turn off printing tools/testing/kunit/kunit.py | 18 +++- tools/testing/kunit/kunit_parser.py | 109 +++++++++++++------------ tools/testing/kunit/kunit_printer.py | 14 +++- tools/testing/kunit/kunit_tool_test.py | 55 +++++++------ 4 files changed, 112 insertions(+), 84 deletions(-) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index bc74088c458a..27c55a7fc1a0 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -23,7 +23,7 @@ from typing import Iterable, List, Optional, Sequence, Tuple import kunit_json import kunit_kernel import kunit_parser -from kunit_printer import stdout +from kunit_printer import stdout, null_printer class KunitStatus(Enum): SUCCESS = auto() @@ -49,6 +49,7 @@ class KunitBuildRequest(KunitConfigRequest): class KunitParseRequest: raw_output: Optional[str] json: Optional[str] + summary: bool @dataclass class KunitExecRequest(KunitParseRequest): @@ -235,11 +236,16 @@ def parse_tests(request: KunitParseRequest, metadata: kunit_json.Metadata, input parse_time = time.time() - parse_start return KunitResult(KunitStatus.SUCCESS, parse_time), fake_test + default_printer = stdout + if request.summary: + default_printer = null_printer # Actually parse the test results. - test = kunit_parser.parse_run_tests(input_data) + test = kunit_parser.parse_run_tests(input_data, default_printer) parse_time = time.time() - parse_start + kunit_parser.print_summary_line(test, stdout) + if request.json: json_str = kunit_json.get_json_result( test=test, @@ -413,6 +419,10 @@ def add_parse_opts(parser: argparse.ArgumentParser) -> None: help='Prints parsed test results as JSON to stdout or a file if ' 'a filename is specified. Does nothing if --raw_output is set.', type=str, const='stdout', default=None, metavar='FILE') + parser.add_argument('--summary', + help='Prints only the summary line for parsed test results.' + 'Does nothing if --raw_output is set.', + action='store_true') def tree_from_args(cli_args: argparse.Namespace) -> kunit_kernel.LinuxSourceTree: @@ -448,6 +458,7 @@ def run_handler(cli_args: argparse.Namespace) -> None: jobs=cli_args.jobs, raw_output=cli_args.raw_output, json=cli_args.json, + summary=cli_args.summary, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, filter=cli_args.filter, @@ -495,6 +506,7 @@ def exec_handler(cli_args: argparse.Namespace) -> None: exec_request = KunitExecRequest(raw_output=cli_args.raw_output, build_dir=cli_args.build_dir, json=cli_args.json, + summary=cli_args.summary, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, filter=cli_args.filter, @@ -520,7 +532,7 @@ def parse_handler(cli_args: argparse.Namespace) -> None: # We know nothing about how the result was created! metadata = kunit_json.Metadata() request = KunitParseRequest(raw_output=cli_args.raw_output, - json=cli_args.json) + json=cli_args.json, summary=cli_args.summary) result, _ = parse_tests(request, metadata, kunit_output) if result.status != KunitStatus.SUCCESS: sys.exit(1) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index ce34be15c929..732f448263de 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -17,7 +17,7 @@ import textwrap from enum import Enum, auto from typing import Iterable, Iterator, List, Optional, Tuple -from kunit_printer import stdout +from kunit_printer import Printer, stdout class Test: """ @@ -54,10 +54,10 @@ class Test: """Returns string representation of a Test class object.""" return str(self) - def add_error(self, error_message: str) -> None: + def add_error(self, printer: Printer, error_message: str) -> None: """Records an error that occurred while parsing this test.""" self.counts.errors += 1 - stdout.print_with_timestamp(stdout.red('[ERROR]') + f' Test: {self.name}: {error_message}') + printer.print_with_timestamp(stdout.red('[ERROR]') + f' Test: {self.name}: {error_message}') def ok_status(self) -> bool: """Returns true if the status was ok, i.e. passed or skipped.""" @@ -251,7 +251,7 @@ KTAP_VERSIONS = [1] TAP_VERSIONS = [13, 14] def check_version(version_num: int, accepted_versions: List[int], - version_type: str, test: Test) -> None: + version_type: str, test: Test, printer: Printer) -> None: """ Adds error to test object if version number is too high or too low. @@ -263,13 +263,14 @@ def check_version(version_num: int, accepted_versions: List[int], version_type - 'KTAP' or 'TAP' depending on the type of version line. test - Test object for current test being parsed + printer - Printer object to output error """ if version_num < min(accepted_versions): - test.add_error(f'{version_type} version lower than expected!') + test.add_error(printer, f'{version_type} version lower than expected!') elif version_num > max(accepted_versions): - test.add_error(f'{version_type} version higer than expected!') + test.add_error(printer, f'{version_type} version higer than expected!') -def parse_ktap_header(lines: LineStream, test: Test) -> bool: +def parse_ktap_header(lines: LineStream, test: Test, printer: Printer) -> bool: """ Parses KTAP/TAP header line and checks version number. Returns False if fails to parse KTAP/TAP header line. @@ -281,6 +282,7 @@ def parse_ktap_header(lines: LineStream, test: Test) -> bool: Parameters: lines - LineStream of KTAP output to parse test - Test object for current test being parsed + printer - Printer object to output results Return: True if successfully parsed KTAP/TAP header line @@ -289,10 +291,10 @@ def parse_ktap_header(lines: LineStream, test: Test) -> bool: tap_match = TAP_START.match(lines.peek()) if ktap_match: version_num = int(ktap_match.group(1)) - check_version(version_num, KTAP_VERSIONS, 'KTAP', test) + check_version(version_num, KTAP_VERSIONS, 'KTAP', test, printer) elif tap_match: version_num = int(tap_match.group(1)) - check_version(version_num, TAP_VERSIONS, 'TAP', test) + check_version(version_num, TAP_VERSIONS, 'TAP', test, printer) else: return False lines.pop() @@ -380,7 +382,7 @@ def peek_test_name_match(lines: LineStream, test: Test) -> bool: return name == test.name def parse_test_result(lines: LineStream, test: Test, - expected_num: int) -> bool: + expected_num: int, printer: Printer) -> bool: """ Parses test result line and stores the status and name in the test object. Reports an error if the test number does not match expected @@ -398,6 +400,7 @@ def parse_test_result(lines: LineStream, test: Test, lines - LineStream of KTAP output to parse test - Test object for current test being parsed expected_num - expected test number for current test + printer - Printer object to output results Return: True if successfully parsed a test result line. @@ -420,7 +423,7 @@ def parse_test_result(lines: LineStream, test: Test, # Check test num num = int(match.group(2)) if num != expected_num: - test.add_error(f'Expected test number {expected_num} but found {num}') + test.add_error(printer, f'Expected test number {expected_num} but found {num}') # Set status of test object status = match.group(1) @@ -486,7 +489,7 @@ def format_test_divider(message: str, len_message: int) -> str: len_2 = difference - len_1 return ('=' * len_1) + f' {message} ' + ('=' * len_2) -def print_test_header(test: Test) -> None: +def print_test_header(test: Test, printer: Printer) -> None: """ Prints test header with test name and optionally the expected number of subtests. @@ -496,6 +499,7 @@ def print_test_header(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object to output results """ message = test.name if message != "": @@ -507,15 +511,15 @@ def print_test_header(test: Test) -> None: message += '(1 subtest)' else: message += f'({test.expected_count} subtests)' - stdout.print_with_timestamp(format_test_divider(message, len(message))) + printer.print_with_timestamp(format_test_divider(message, len(message))) -def print_log(log: Iterable[str]) -> None: +def print_log(log: Iterable[str], printer: Printer) -> None: """Prints all strings in saved log for test in yellow.""" formatted = textwrap.dedent('\n'.join(log)) for line in formatted.splitlines(): - stdout.print_with_timestamp(stdout.yellow(line)) + printer.print_with_timestamp(printer.yellow(line)) -def format_test_result(test: Test) -> str: +def format_test_result(test: Test, printer: Printer) -> str: """ Returns string with formatted test result with colored status and test name. @@ -525,23 +529,24 @@ def format_test_result(test: Test) -> str: Parameters: test - Test object representing current test being printed + printer - Printer object to output results Return: String containing formatted test result """ if test.status == TestStatus.SUCCESS: - return stdout.green('[PASSED] ') + test.name + return printer.green('[PASSED] ') + test.name if test.status == TestStatus.SKIPPED: - return stdout.yellow('[SKIPPED] ') + test.name + return printer.yellow('[SKIPPED] ') + test.name if test.status == TestStatus.NO_TESTS: - return stdout.yellow('[NO TESTS RUN] ') + test.name + return printer.yellow('[NO TESTS RUN] ') + test.name if test.status == TestStatus.TEST_CRASHED: - print_log(test.log) + print_log(test.log, printer) return stdout.red('[CRASHED] ') + test.name - print_log(test.log) - return stdout.red('[FAILED] ') + test.name + print_log(test.log, printer) + return printer.red('[FAILED] ') + test.name -def print_test_result(test: Test) -> None: +def print_test_result(test: Test, printer: Printer) -> None: """ Prints result line with status of test. @@ -550,10 +555,11 @@ def print_test_result(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object """ - stdout.print_with_timestamp(format_test_result(test)) + printer.print_with_timestamp(format_test_result(test, printer)) -def print_test_footer(test: Test) -> None: +def print_test_footer(test: Test, printer: Printer) -> None: """ Prints test footer with status of test. @@ -562,10 +568,11 @@ def print_test_footer(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object to output results """ - message = format_test_result(test) - stdout.print_with_timestamp(format_test_divider(message, - len(message) - stdout.color_len())) + message = format_test_result(test, printer) + printer.print_with_timestamp(format_test_divider(message, + len(message) - printer.color_len())) @@ -601,7 +608,7 @@ def _summarize_failed_tests(test: Test) -> str: return 'Failures: ' + ', '.join(failures) -def print_summary_line(test: Test) -> None: +def print_summary_line(test: Test, printer: Printer) -> None: """ Prints summary line of test object. Color of line is dependent on status of test. Color is green if test passes, yellow if test is @@ -614,6 +621,7 @@ def print_summary_line(test: Test) -> None: Errors: 0" test - Test object representing current test being printed + printer - Printer object to output results """ if test.status == TestStatus.SUCCESS: color = stdout.green @@ -621,7 +629,7 @@ def print_summary_line(test: Test) -> None: color = stdout.yellow else: color = stdout.red - stdout.print_with_timestamp(color(f'Testing complete. {test.counts}')) + printer.print_with_timestamp(color(f'Testing complete. {test.counts}')) # Summarize failures that might have gone off-screen since we had a lot # of tests (arbitrarily defined as >=100 for now). @@ -630,7 +638,7 @@ def print_summary_line(test: Test) -> None: summarized = _summarize_failed_tests(test) if not summarized: return - stdout.print_with_timestamp(color(summarized)) + printer.print_with_timestamp(color(summarized)) # Other methods: @@ -654,7 +662,7 @@ def bubble_up_test_results(test: Test) -> None: elif test.counts.get_status() == TestStatus.TEST_CRASHED: test.status = TestStatus.TEST_CRASHED -def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: bool) -> Test: +def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: bool, printer: Printer) -> Test: """ Finds next test to parse in LineStream, creates new Test object, parses any subtests of the test, populates Test object with all @@ -710,6 +718,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: log - list of strings containing any preceding diagnostic lines corresponding to the current test is_subtest - boolean indicating whether test is a subtest + printer - Printer object to output results Return: Test object populated with characteristics and any subtests @@ -725,14 +734,14 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If parsing the main/top-level test, parse KTAP version line and # test plan test.name = "main" - ktap_line = parse_ktap_header(lines, test) + ktap_line = parse_ktap_header(lines, test, printer) test.log.extend(parse_diagnostic(lines)) parse_test_plan(lines, test) parent_test = True else: # If not the main test, attempt to parse a test header containing # the KTAP version line and/or subtest header line - ktap_line = parse_ktap_header(lines, test) + ktap_line = parse_ktap_header(lines, test, printer) subtest_line = parse_test_header(lines, test) parent_test = (ktap_line or subtest_line) if parent_test: @@ -740,7 +749,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # to parse test plan and print test header test.log.extend(parse_diagnostic(lines)) parse_test_plan(lines, test) - print_test_header(test) + print_test_header(test, printer) expected_count = test.expected_count subtests = [] test_num = 1 @@ -758,16 +767,16 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If parser reaches end of test before # parsing expected number of subtests, print # crashed subtest and record error - test.add_error('missing expected subtest!') + test.add_error(printer, 'missing expected subtest!') sub_test.log.extend(sub_log) test.counts.add_status( TestStatus.TEST_CRASHED) - print_test_result(sub_test) + print_test_result(sub_test, printer) else: test.log.extend(sub_log) break else: - sub_test = parse_test(lines, test_num, sub_log, True) + sub_test = parse_test(lines, test_num, sub_log, True, printer) subtests.append(sub_test) test_num += 1 test.subtests = subtests @@ -775,51 +784,51 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If not main test, look for test result line test.log.extend(parse_diagnostic(lines)) if test.name != "" and not peek_test_name_match(lines, test): - test.add_error('missing subtest result line!') + test.add_error(printer, 'missing subtest result line!') else: - parse_test_result(lines, test, expected_num) + parse_test_result(lines, test, expected_num, printer) # Check for there being no subtests within parent test if parent_test and len(subtests) == 0: # Don't override a bad status if this test had one reported. # Assumption: no subtests means CRASHED is from Test.__init__() if test.status in (TestStatus.TEST_CRASHED, TestStatus.SUCCESS): - print_log(test.log) + print_log(test.log, printer) test.status = TestStatus.NO_TESTS - test.add_error('0 tests run!') + test.add_error(printer, '0 tests run!') # Add statuses to TestCounts attribute in Test object bubble_up_test_results(test) if parent_test and is_subtest: # If test has subtests and is not the main test object, print # footer. - print_test_footer(test) + print_test_footer(test, printer) elif is_subtest: - print_test_result(test) + print_test_result(test, printer) return test -def parse_run_tests(kernel_output: Iterable[str]) -> Test: +def parse_run_tests(kernel_output: Iterable[str], printer: Printer) -> Test: """ Using kernel output, extract KTAP lines, parse the lines for test results and print condensed test results and summary line. Parameters: kernel_output - Iterable object contains lines of kernel output + printer - Printer object to output results Return: Test - the main test object with all subtests. """ - stdout.print_with_timestamp(DIVIDER) + printer.print_with_timestamp(DIVIDER) lines = extract_tap_lines(kernel_output) test = Test() if not lines: test.name = '<missing>' - test.add_error('Could not find any KTAP output. Did any KUnit tests run?') + test.add_error(printer, 'Could not find any KTAP output. Did any KUnit tests run?') test.status = TestStatus.FAILURE_TO_PARSE_TESTS else: - test = parse_test(lines, 0, [], False) + test = parse_test(lines, 0, [], False, printer) if test.status != TestStatus.NO_TESTS: test.status = test.counts.get_status() - stdout.print_with_timestamp(DIVIDER) - print_summary_line(test) + printer.print_with_timestamp(DIVIDER) return test diff --git a/tools/testing/kunit/kunit_printer.py b/tools/testing/kunit/kunit_printer.py index 015adf87dc2c..ca119f61fe79 100644 --- a/tools/testing/kunit/kunit_printer.py +++ b/tools/testing/kunit/kunit_printer.py @@ -15,12 +15,17 @@ _RESET = '\033[0;0m' class Printer: """Wraps a file object, providing utilities for coloring output, etc.""" - def __init__(self, output: typing.IO[str]): + def __init__(self, print: bool=True, output: typing.IO[str]=sys.stdout): self._output = output - self._use_color = output.isatty() + self._print = print + if print: + self._use_color = output.isatty() + else: + self._use_color = False def print(self, message: str) -> None: - print(message, file=self._output) + if self._print: + print(message, file=self._output) def print_with_timestamp(self, message: str) -> None: ts = datetime.datetime.now().strftime('%H:%M:%S') @@ -45,4 +50,5 @@ class Printer: return len(self.red('')) # Provides a default instance that prints to stdout -stdout = Printer(sys.stdout) +stdout = Printer() +null_printer = Printer(print=False) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 2beb7327e53f..02aa296d8850 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -23,6 +23,7 @@ import kunit_parser import kunit_kernel import kunit_json import kunit +from kunit_printer import stdout test_tmpdir = '' abs_test_data_dir = '' @@ -139,28 +140,28 @@ class KUnitParserTest(unittest.TestCase): def test_parse_successful_test_log(self): all_passed_log = test_data_path('test_is_test_passed-all_passed.log') with open(all_passed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_parse_successful_nested_tests_log(self): all_passed_log = test_data_path('test_is_test_passed-all_passed_nested.log') with open(all_passed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_kselftest_nested(self): kselftest_log = test_data_path('test_is_test_passed-kselftest.log') with open(kselftest_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_parse_failed_test_log(self): failed_log = test_data_path('test_is_test_passed-failure.log') with open(failed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.assertEqual(result.counts.errors, 0) @@ -168,7 +169,7 @@ class KUnitParserTest(unittest.TestCase): empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log') with open(empty_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests)) self.assertEqual(kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS, result.status) self.assertEqual(result.counts.errors, 1) @@ -179,7 +180,7 @@ class KUnitParserTest(unittest.TestCase): with open(missing_plan_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines( - file.readlines())) + file.readlines()), stdout) # A missing test plan is not an error. self.assertEqual(result.counts, kunit_parser.TestCounts(passed=10, errors=0)) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -188,7 +189,7 @@ class KUnitParserTest(unittest.TestCase): header_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') with open(header_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests)) self.assertEqual(kunit_parser.TestStatus.NO_TESTS, result.status) self.assertEqual(result.counts.errors, 1) @@ -197,7 +198,7 @@ class KUnitParserTest(unittest.TestCase): no_plan_log = test_data_path('test_is_test_passed-no_tests_no_plan.log') with open(no_plan_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests[0].subtests[0].subtests)) self.assertEqual( kunit_parser.TestStatus.NO_TESTS, @@ -210,7 +211,7 @@ class KUnitParserTest(unittest.TestCase): print_mock = mock.patch('kunit_printer.Printer.print').start() with open(crash_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) print_mock.assert_any_call(StrContains('Could not find any KTAP output.')) print_mock.stop() self.assertEqual(0, len(result.subtests)) @@ -219,7 +220,7 @@ class KUnitParserTest(unittest.TestCase): def test_skipped_test(self): skipped_log = test_data_path('test_skip_tests.log') with open(skipped_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # A skipped test does not fail the whole suite. self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -228,7 +229,7 @@ class KUnitParserTest(unittest.TestCase): def test_skipped_all_tests(self): skipped_log = test_data_path('test_skip_all_tests.log') with open(skipped_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SKIPPED, result.status) self.assertEqual(result.counts, kunit_parser.TestCounts(skipped=5)) @@ -236,7 +237,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_hyphen(self): hyphen_log = test_data_path('test_strip_hyphen.log') with open(hyphen_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # A skipped test does not fail the whole suite. self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -250,7 +251,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_prefix_printk_time(self): prefix_log = test_data_path('test_config_printk_time.log') with open(prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -258,7 +259,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_multiple_prefixes(self): prefix_log = test_data_path('test_multiple_prefixes.log') with open(prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -266,7 +267,7 @@ class KUnitParserTest(unittest.TestCase): def test_prefix_mixed_kernel_output(self): mixed_prefix_log = test_data_path('test_interrupted_tap_output.log') with open(mixed_prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -274,7 +275,7 @@ class KUnitParserTest(unittest.TestCase): def test_prefix_poundsign(self): pound_log = test_data_path('test_pound_sign.log') with open(pound_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -282,7 +283,7 @@ class KUnitParserTest(unittest.TestCase): def test_kernel_panic_end(self): panic_log = test_data_path('test_kernel_panic_interrupt.log') with open(panic_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.TEST_CRASHED, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertGreaterEqual(result.counts.errors, 1) @@ -290,7 +291,7 @@ class KUnitParserTest(unittest.TestCase): def test_pound_no_prefix(self): pound_log = test_data_path('test_pound_no_prefix.log') with open(pound_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -310,7 +311,7 @@ class KUnitParserTest(unittest.TestCase): not ok 2 - test2 not ok 1 - some_failed_suite """ - result = kunit_parser.parse_run_tests(output.splitlines()) + result = kunit_parser.parse_run_tests(output.splitlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.assertEqual(kunit_parser._summarize_failed_tests(result), @@ -319,7 +320,7 @@ class KUnitParserTest(unittest.TestCase): def test_ktap_format(self): ktap_log = test_data_path('test_parse_ktap_output.log') with open(ktap_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(result.counts, kunit_parser.TestCounts(passed=3)) self.assertEqual('suite', result.subtests[0].name) self.assertEqual('case_1', result.subtests[0].subtests[0].name) @@ -328,13 +329,13 @@ class KUnitParserTest(unittest.TestCase): def test_parse_subtest_header(self): ktap_log = test_data_path('test_parse_subtest_header.log') with open(ktap_log) as file: - kunit_parser.parse_run_tests(file.readlines()) + kunit_parser.parse_run_tests(file.readlines(), stdout) self.print_mock.assert_any_call(StrContains('suite (1 subtest)')) def test_parse_attributes(self): ktap_log = test_data_path('test_parse_attributes.log') with open(ktap_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # Test should pass with no errors self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=0)) @@ -355,7 +356,7 @@ class KUnitParserTest(unittest.TestCase): Indented more. not ok 1 test1 """ - result = kunit_parser.parse_run_tests(output.splitlines()) + result = kunit_parser.parse_run_tests(output.splitlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.print_mock.assert_any_call(StrContains('Test output.')) @@ -544,7 +545,7 @@ class KUnitJsonTest(unittest.TestCase): def _json_for(self, log_file): with open(test_data_path(log_file)) as file: - test_result = kunit_parser.parse_run_tests(file) + test_result = kunit_parser.parse_run_tests(file, stdout) json_obj = kunit_json.get_json_result( test=test_result, metadata=kunit_json.Metadata()) @@ -810,7 +811,7 @@ class KUnitMainTest(unittest.TestCase): self.linux_source_mock.run_kernel.return_value = ['TAP version 14', 'init: random output'] + want got = kunit._list_tests(self.linux_source_mock, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'suite', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*', '', None, None, 'suite', False, False)) self.assertEqual(got, want) # Should respect the user's filter glob when listing tests. self.linux_source_mock.run_kernel.assert_called_once_with( @@ -823,7 +824,7 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*.test*', '', None, None, 'suite', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*.test*', '', None, None, 'suite', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ mock.call(args=None, build_dir='.kunit', filter_glob='suite.test*', filter='', filter_action=None, timeout=300), mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test*', filter='', filter_action=None, timeout=300), @@ -836,7 +837,7 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'test', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*', '', None, None, 'test', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ mock.call(args=None, build_dir='.kunit', filter_glob='suite.test1', filter='', filter_action=None, timeout=300), mock.call(args=None, build_dir='.kunit', filter_glob='suite.test2', filter='', filter_action=None, timeout=300), base-commit: ff6d85216d9f632f62ad8130d3c4a4b267e45048 -- 2.47.0.277.g8800431eea-goog

1 year

2
2
0 0

Re: [PATCH 2/3] KVM: x86: Add support for VMware guest specific hypercalls

by Sean Christopherson

On Wed, Nov 13, 2024, Paolo Bonzini wrote: > Il mar 12 nov 2024, 21:44 Doug Covelli <doug.covelli(a)broadcom.com> ha > scritto: > > > > Split irqchip should be the best tradeoff. Without it, moves from cr8 > > > stay in the kernel, but moves to cr8 always go to userspace with a > > > KVM_EXIT_SET_TPR exit. You also won't be able to use Intel > > > flexpriority (in-processor accelerated TPR) because KVM does not know > > > which bits are set in IRR. So it will be *really* every move to cr8 > > > that goes to userspace. > > > > Sorry to hijack this thread but is there a technical reason not to allow > > CR8 based accesses to the TPR (not MMIO accesses) when the in-kernel local > > APIC is not in use? > > No worries, you're not hijacking :) The only reason is that it would be > more code for a seldom used feature and anyway with worse performance. (To > be clear, CR8 based accesses are allowed, but stores cause an exit in order > to check the new TPR against IRR. That's because KVM's API does not have an > equivalent of the TPR threshold as you point out below). > > > Also I could not find these documented anywhere but with MSFT's APIC our > > monitor relies on extensions for trapping certain events such as INIT/SIPI > > plus LINT0 and SVR writes: > > > > UINT64 X64ApicInitSipiExitTrap : 1; // > > WHvRunVpExitReasonX64ApicInitSipiTrap > > UINT64 X64ApicWriteLint0ExitTrap : 1; // > > WHvRunVpExitReasonX64ApicWriteTrap > > UINT64 X64ApicWriteLint1ExitTrap : 1; // > > WHvRunVpExitReasonX64ApicWriteTrap > > UINT64 X64ApicWriteSvrExitTrap : 1; // > > WHvRunVpExitReasonX64ApicWriteTrap > > > > There's no need for this in KVM's in-kernel APIC model. INIT and SIPI are > handled in the hypervisor and you can get the current state of APs via > KVM_GET_MPSTATE. LINT0 and LINT1 are injected with KVM_INTERRUPT and > KVM_NMI respectively, and they obey IF/PPR and NMI blocking respectively, > plus the interrupt shadow; so there's no need for userspace to know when > LINT0/LINT1 themselves change. The spurious interrupt vector register is > also handled completely in kernel. > > > I did not see any similar functionality for KVM. Does anything like that > > exist? In any case we would be happy to add support for handling CR8 > > accesses w/o exiting w/o the in-kernel APIC along with some sort of a way > > to configure the TPR threshold if folks are not opposed to that. > > As far I know everybody who's using KVM (whether proprietary or open > source) has had no need for that, so I don't think it's a good idea to make > the API more complex. +1 > Performance of Windows guests is going to be bad anyway with userspace APIC. Heh, on modern hardware, performance of any guest is going to suck with a userspace APIC, compared to what is possible with an in-kernel APIC. More importantly, I really, really don't want to encourage non-trivial usage of a local APIC in userspace. KVM's support for a userspace local APIC is very poorly tested these days. I have zero desire to spend any amount of time reviewing and fixing issues that are unique to emulating the local APIC in userspace. And long term, I would love to force an in-kernel local APIC, though I don't know if that's entirely feasible.

1 year

1
0
0 0

[PATCH net-next v3 7/7] selftests: net: fdb_notify: Add a test for FDB notifications

by Petr Machata

Check that only one notification is produced for various FDB edit operations. Regarding the ip_link_add() and ip_link_master() helpers. This pattern of action plus corresponding defer is bound to come up often, and a dedicated vocabulary to capture it will be handy. tunnel_create() and vlan_create() from forwarding/lib.sh are somewhat opaque and perhaps too kitchen-sinky, so I tried to go in the opposite direction with these ones, and wrapped only the bare minimum to schedule a corresponding cleanup. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/fdb_notify.sh | 95 +++++++++++++++++++++++ tools/testing/selftests/net/lib.sh | 17 ++++ 3 files changed, 113 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/fdb_notify.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 26a4883a65c9..ab0e8f30bfe7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -92,7 +92,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh -TEST_PROGS += fdb_flush.sh +TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh new file mode 100755 index 000000000000..a98047361988 --- /dev/null +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -0,0 +1,95 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +ALL_TESTS=" + test_dup_bridge + test_dup_vxlan_self + test_dup_vxlan_master + test_dup_macvlan_self + test_dup_macvlan_master +" + +do_test_dup() +{ + local op=$1; shift + local what=$1; shift + local tmpf + + RET=0 + + tmpf=$(mktemp) + defer rm "$tmpf" + + defer_scope_push + bridge monitor fdb &> "$tmpf" & + defer kill_process $! + + bridge fdb "$op" 00:11:22:33:44:55 vlan 1 "$@" + sleep 0.2 + defer_scope_pop + + local count=$(grep -c -e 00:11:22:33:44:55 $tmpf) + ((count == 1)) + check_err $? "Got $count notifications, expected 1" + + log_test "$what $op: Duplicate notifications" +} + +test_dup_bridge() +{ + ip_link_add br up type bridge vlan_filtering 1 + do_test_dup add "bridge" dev br self + do_test_dup del "bridge" dev br self +} + +test_dup_vxlan_self() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan" dev vx self dst 192.0.2.1 + do_test_dup del "vxlan" dev vx self dst 192.0.2.1 +} + +test_dup_vxlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan master" dev vx master + do_test_dup del "vxlan master" dev vx master +} + +test_dup_macvlan_self() +{ + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + + do_test_dup add "macvlan self" dev mv self + do_test_dup del "macvlan self" dev mv self +} + +test_dup_macvlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + ip_link_master mv br + + do_test_dup add "macvlan master" dev mv self + do_test_dup del "macvlan master" dev mv self +} + +cleanup() +{ + defer_scopes_cleanup +} + +trap cleanup EXIT +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 24f63e45735d..8994fec1c38f 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -442,3 +442,20 @@ kill_process() # Suppress noise from killing the process. { kill $pid && wait $pid; } 2>/dev/null } + +ip_link_add() +{ + local name=$1; shift + + ip link add name "$name" "$@" + defer ip link del dev "$name" +} + +ip_link_master() +{ + local member=$1; shift + local master=$1; shift + + ip link set dev "$member" master "$master" + defer ip link set dev "$member" nomaster +} -- 2.45.0

1 year

2
2
0 0

[PATCH 1/2] kunit: tool: Only print the summary

by Rae Moar

From: David Gow <davidgow(a)google.com> Allow only printing the summary at the end of a test run, rather than all individual test results. This summary will list a few failing tests if there are any. To use: ./tools/testing/kunit/kunit.py run --summary Signed-off-by: Rae Moar <rmoar(a)google.com> Signed-off-by: David Gow <davidgow(a)google.com> --- tools/testing/kunit/kunit.py | 18 +++- tools/testing/kunit/kunit_parser.py | 109 +++++++++++++------------ tools/testing/kunit/kunit_printer.py | 7 +- tools/testing/kunit/kunit_tool_test.py | 55 +++++++------ 4 files changed, 107 insertions(+), 82 deletions(-) diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index bc74088c458a..27c55a7fc1a0 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -23,7 +23,7 @@ from typing import Iterable, List, Optional, Sequence, Tuple import kunit_json import kunit_kernel import kunit_parser -from kunit_printer import stdout +from kunit_printer import stdout, null_printer class KunitStatus(Enum): SUCCESS = auto() @@ -49,6 +49,7 @@ class KunitBuildRequest(KunitConfigRequest): class KunitParseRequest: raw_output: Optional[str] json: Optional[str] + summary: bool @dataclass class KunitExecRequest(KunitParseRequest): @@ -235,11 +236,16 @@ def parse_tests(request: KunitParseRequest, metadata: kunit_json.Metadata, input parse_time = time.time() - parse_start return KunitResult(KunitStatus.SUCCESS, parse_time), fake_test + default_printer = stdout + if request.summary: + default_printer = null_printer # Actually parse the test results. - test = kunit_parser.parse_run_tests(input_data) + test = kunit_parser.parse_run_tests(input_data, default_printer) parse_time = time.time() - parse_start + kunit_parser.print_summary_line(test, stdout) + if request.json: json_str = kunit_json.get_json_result( test=test, @@ -413,6 +419,10 @@ def add_parse_opts(parser: argparse.ArgumentParser) -> None: help='Prints parsed test results as JSON to stdout or a file if ' 'a filename is specified. Does nothing if --raw_output is set.', type=str, const='stdout', default=None, metavar='FILE') + parser.add_argument('--summary', + help='Prints only the summary line for parsed test results.' + 'Does nothing if --raw_output is set.', + action='store_true') def tree_from_args(cli_args: argparse.Namespace) -> kunit_kernel.LinuxSourceTree: @@ -448,6 +458,7 @@ def run_handler(cli_args: argparse.Namespace) -> None: jobs=cli_args.jobs, raw_output=cli_args.raw_output, json=cli_args.json, + summary=cli_args.summary, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, filter=cli_args.filter, @@ -495,6 +506,7 @@ def exec_handler(cli_args: argparse.Namespace) -> None: exec_request = KunitExecRequest(raw_output=cli_args.raw_output, build_dir=cli_args.build_dir, json=cli_args.json, + summary=cli_args.summary, timeout=cli_args.timeout, filter_glob=cli_args.filter_glob, filter=cli_args.filter, @@ -520,7 +532,7 @@ def parse_handler(cli_args: argparse.Namespace) -> None: # We know nothing about how the result was created! metadata = kunit_json.Metadata() request = KunitParseRequest(raw_output=cli_args.raw_output, - json=cli_args.json) + json=cli_args.json, summary=cli_args.summary) result, _ = parse_tests(request, metadata, kunit_output) if result.status != KunitStatus.SUCCESS: sys.exit(1) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index ce34be15c929..732f448263de 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -17,7 +17,7 @@ import textwrap from enum import Enum, auto from typing import Iterable, Iterator, List, Optional, Tuple -from kunit_printer import stdout +from kunit_printer import Printer, stdout class Test: """ @@ -54,10 +54,10 @@ class Test: """Returns string representation of a Test class object.""" return str(self) - def add_error(self, error_message: str) -> None: + def add_error(self, printer: Printer, error_message: str) -> None: """Records an error that occurred while parsing this test.""" self.counts.errors += 1 - stdout.print_with_timestamp(stdout.red('[ERROR]') + f' Test: {self.name}: {error_message}') + printer.print_with_timestamp(stdout.red('[ERROR]') + f' Test: {self.name}: {error_message}') def ok_status(self) -> bool: """Returns true if the status was ok, i.e. passed or skipped.""" @@ -251,7 +251,7 @@ KTAP_VERSIONS = [1] TAP_VERSIONS = [13, 14] def check_version(version_num: int, accepted_versions: List[int], - version_type: str, test: Test) -> None: + version_type: str, test: Test, printer: Printer) -> None: """ Adds error to test object if version number is too high or too low. @@ -263,13 +263,14 @@ def check_version(version_num: int, accepted_versions: List[int], version_type - 'KTAP' or 'TAP' depending on the type of version line. test - Test object for current test being parsed + printer - Printer object to output error """ if version_num < min(accepted_versions): - test.add_error(f'{version_type} version lower than expected!') + test.add_error(printer, f'{version_type} version lower than expected!') elif version_num > max(accepted_versions): - test.add_error(f'{version_type} version higer than expected!') + test.add_error(printer, f'{version_type} version higer than expected!') -def parse_ktap_header(lines: LineStream, test: Test) -> bool: +def parse_ktap_header(lines: LineStream, test: Test, printer: Printer) -> bool: """ Parses KTAP/TAP header line and checks version number. Returns False if fails to parse KTAP/TAP header line. @@ -281,6 +282,7 @@ def parse_ktap_header(lines: LineStream, test: Test) -> bool: Parameters: lines - LineStream of KTAP output to parse test - Test object for current test being parsed + printer - Printer object to output results Return: True if successfully parsed KTAP/TAP header line @@ -289,10 +291,10 @@ def parse_ktap_header(lines: LineStream, test: Test) -> bool: tap_match = TAP_START.match(lines.peek()) if ktap_match: version_num = int(ktap_match.group(1)) - check_version(version_num, KTAP_VERSIONS, 'KTAP', test) + check_version(version_num, KTAP_VERSIONS, 'KTAP', test, printer) elif tap_match: version_num = int(tap_match.group(1)) - check_version(version_num, TAP_VERSIONS, 'TAP', test) + check_version(version_num, TAP_VERSIONS, 'TAP', test, printer) else: return False lines.pop() @@ -380,7 +382,7 @@ def peek_test_name_match(lines: LineStream, test: Test) -> bool: return name == test.name def parse_test_result(lines: LineStream, test: Test, - expected_num: int) -> bool: + expected_num: int, printer: Printer) -> bool: """ Parses test result line and stores the status and name in the test object. Reports an error if the test number does not match expected @@ -398,6 +400,7 @@ def parse_test_result(lines: LineStream, test: Test, lines - LineStream of KTAP output to parse test - Test object for current test being parsed expected_num - expected test number for current test + printer - Printer object to output results Return: True if successfully parsed a test result line. @@ -420,7 +423,7 @@ def parse_test_result(lines: LineStream, test: Test, # Check test num num = int(match.group(2)) if num != expected_num: - test.add_error(f'Expected test number {expected_num} but found {num}') + test.add_error(printer, f'Expected test number {expected_num} but found {num}') # Set status of test object status = match.group(1) @@ -486,7 +489,7 @@ def format_test_divider(message: str, len_message: int) -> str: len_2 = difference - len_1 return ('=' * len_1) + f' {message} ' + ('=' * len_2) -def print_test_header(test: Test) -> None: +def print_test_header(test: Test, printer: Printer) -> None: """ Prints test header with test name and optionally the expected number of subtests. @@ -496,6 +499,7 @@ def print_test_header(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object to output results """ message = test.name if message != "": @@ -507,15 +511,15 @@ def print_test_header(test: Test) -> None: message += '(1 subtest)' else: message += f'({test.expected_count} subtests)' - stdout.print_with_timestamp(format_test_divider(message, len(message))) + printer.print_with_timestamp(format_test_divider(message, len(message))) -def print_log(log: Iterable[str]) -> None: +def print_log(log: Iterable[str], printer: Printer) -> None: """Prints all strings in saved log for test in yellow.""" formatted = textwrap.dedent('\n'.join(log)) for line in formatted.splitlines(): - stdout.print_with_timestamp(stdout.yellow(line)) + printer.print_with_timestamp(printer.yellow(line)) -def format_test_result(test: Test) -> str: +def format_test_result(test: Test, printer: Printer) -> str: """ Returns string with formatted test result with colored status and test name. @@ -525,23 +529,24 @@ def format_test_result(test: Test) -> str: Parameters: test - Test object representing current test being printed + printer - Printer object to output results Return: String containing formatted test result """ if test.status == TestStatus.SUCCESS: - return stdout.green('[PASSED] ') + test.name + return printer.green('[PASSED] ') + test.name if test.status == TestStatus.SKIPPED: - return stdout.yellow('[SKIPPED] ') + test.name + return printer.yellow('[SKIPPED] ') + test.name if test.status == TestStatus.NO_TESTS: - return stdout.yellow('[NO TESTS RUN] ') + test.name + return printer.yellow('[NO TESTS RUN] ') + test.name if test.status == TestStatus.TEST_CRASHED: - print_log(test.log) + print_log(test.log, printer) return stdout.red('[CRASHED] ') + test.name - print_log(test.log) - return stdout.red('[FAILED] ') + test.name + print_log(test.log, printer) + return printer.red('[FAILED] ') + test.name -def print_test_result(test: Test) -> None: +def print_test_result(test: Test, printer: Printer) -> None: """ Prints result line with status of test. @@ -550,10 +555,11 @@ def print_test_result(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object """ - stdout.print_with_timestamp(format_test_result(test)) + printer.print_with_timestamp(format_test_result(test, printer)) -def print_test_footer(test: Test) -> None: +def print_test_footer(test: Test, printer: Printer) -> None: """ Prints test footer with status of test. @@ -562,10 +568,11 @@ def print_test_footer(test: Test) -> None: Parameters: test - Test object representing current test being printed + printer - Printer object to output results """ - message = format_test_result(test) - stdout.print_with_timestamp(format_test_divider(message, - len(message) - stdout.color_len())) + message = format_test_result(test, printer) + printer.print_with_timestamp(format_test_divider(message, + len(message) - printer.color_len())) @@ -601,7 +608,7 @@ def _summarize_failed_tests(test: Test) -> str: return 'Failures: ' + ', '.join(failures) -def print_summary_line(test: Test) -> None: +def print_summary_line(test: Test, printer: Printer) -> None: """ Prints summary line of test object. Color of line is dependent on status of test. Color is green if test passes, yellow if test is @@ -614,6 +621,7 @@ def print_summary_line(test: Test) -> None: Errors: 0" test - Test object representing current test being printed + printer - Printer object to output results """ if test.status == TestStatus.SUCCESS: color = stdout.green @@ -621,7 +629,7 @@ def print_summary_line(test: Test) -> None: color = stdout.yellow else: color = stdout.red - stdout.print_with_timestamp(color(f'Testing complete. {test.counts}')) + printer.print_with_timestamp(color(f'Testing complete. {test.counts}')) # Summarize failures that might have gone off-screen since we had a lot # of tests (arbitrarily defined as >=100 for now). @@ -630,7 +638,7 @@ def print_summary_line(test: Test) -> None: summarized = _summarize_failed_tests(test) if not summarized: return - stdout.print_with_timestamp(color(summarized)) + printer.print_with_timestamp(color(summarized)) # Other methods: @@ -654,7 +662,7 @@ def bubble_up_test_results(test: Test) -> None: elif test.counts.get_status() == TestStatus.TEST_CRASHED: test.status = TestStatus.TEST_CRASHED -def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: bool) -> Test: +def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: bool, printer: Printer) -> Test: """ Finds next test to parse in LineStream, creates new Test object, parses any subtests of the test, populates Test object with all @@ -710,6 +718,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: log - list of strings containing any preceding diagnostic lines corresponding to the current test is_subtest - boolean indicating whether test is a subtest + printer - Printer object to output results Return: Test object populated with characteristics and any subtests @@ -725,14 +734,14 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If parsing the main/top-level test, parse KTAP version line and # test plan test.name = "main" - ktap_line = parse_ktap_header(lines, test) + ktap_line = parse_ktap_header(lines, test, printer) test.log.extend(parse_diagnostic(lines)) parse_test_plan(lines, test) parent_test = True else: # If not the main test, attempt to parse a test header containing # the KTAP version line and/or subtest header line - ktap_line = parse_ktap_header(lines, test) + ktap_line = parse_ktap_header(lines, test, printer) subtest_line = parse_test_header(lines, test) parent_test = (ktap_line or subtest_line) if parent_test: @@ -740,7 +749,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # to parse test plan and print test header test.log.extend(parse_diagnostic(lines)) parse_test_plan(lines, test) - print_test_header(test) + print_test_header(test, printer) expected_count = test.expected_count subtests = [] test_num = 1 @@ -758,16 +767,16 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If parser reaches end of test before # parsing expected number of subtests, print # crashed subtest and record error - test.add_error('missing expected subtest!') + test.add_error(printer, 'missing expected subtest!') sub_test.log.extend(sub_log) test.counts.add_status( TestStatus.TEST_CRASHED) - print_test_result(sub_test) + print_test_result(sub_test, printer) else: test.log.extend(sub_log) break else: - sub_test = parse_test(lines, test_num, sub_log, True) + sub_test = parse_test(lines, test_num, sub_log, True, printer) subtests.append(sub_test) test_num += 1 test.subtests = subtests @@ -775,51 +784,51 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: # If not main test, look for test result line test.log.extend(parse_diagnostic(lines)) if test.name != "" and not peek_test_name_match(lines, test): - test.add_error('missing subtest result line!') + test.add_error(printer, 'missing subtest result line!') else: - parse_test_result(lines, test, expected_num) + parse_test_result(lines, test, expected_num, printer) # Check for there being no subtests within parent test if parent_test and len(subtests) == 0: # Don't override a bad status if this test had one reported. # Assumption: no subtests means CRASHED is from Test.__init__() if test.status in (TestStatus.TEST_CRASHED, TestStatus.SUCCESS): - print_log(test.log) + print_log(test.log, printer) test.status = TestStatus.NO_TESTS - test.add_error('0 tests run!') + test.add_error(printer, '0 tests run!') # Add statuses to TestCounts attribute in Test object bubble_up_test_results(test) if parent_test and is_subtest: # If test has subtests and is not the main test object, print # footer. - print_test_footer(test) + print_test_footer(test, printer) elif is_subtest: - print_test_result(test) + print_test_result(test, printer) return test -def parse_run_tests(kernel_output: Iterable[str]) -> Test: +def parse_run_tests(kernel_output: Iterable[str], printer: Printer) -> Test: """ Using kernel output, extract KTAP lines, parse the lines for test results and print condensed test results and summary line. Parameters: kernel_output - Iterable object contains lines of kernel output + printer - Printer object to output results Return: Test - the main test object with all subtests. """ - stdout.print_with_timestamp(DIVIDER) + printer.print_with_timestamp(DIVIDER) lines = extract_tap_lines(kernel_output) test = Test() if not lines: test.name = '<missing>' - test.add_error('Could not find any KTAP output. Did any KUnit tests run?') + test.add_error(printer, 'Could not find any KTAP output. Did any KUnit tests run?') test.status = TestStatus.FAILURE_TO_PARSE_TESTS else: - test = parse_test(lines, 0, [], False) + test = parse_test(lines, 0, [], False, printer) if test.status != TestStatus.NO_TESTS: test.status = test.counts.get_status() - stdout.print_with_timestamp(DIVIDER) - print_summary_line(test) + printer.print_with_timestamp(DIVIDER) return test diff --git a/tools/testing/kunit/kunit_printer.py b/tools/testing/kunit/kunit_printer.py index 015adf87dc2c..2c55b4b67bfc 100644 --- a/tools/testing/kunit/kunit_printer.py +++ b/tools/testing/kunit/kunit_printer.py @@ -17,10 +17,12 @@ class Printer: def __init__(self, output: typing.IO[str]): self._output = output - self._use_color = output.isatty() + if output is not None: + self._use_color = output.isatty() def print(self, message: str) -> None: - print(message, file=self._output) + if self._output is not None: + print(message, file=self._output) def print_with_timestamp(self, message: str) -> None: ts = datetime.datetime.now().strftime('%H:%M:%S') @@ -46,3 +48,4 @@ class Printer: # Provides a default instance that prints to stdout stdout = Printer(sys.stdout) +null_printer = Printer(None) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 2beb7327e53f..02aa296d8850 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -23,6 +23,7 @@ import kunit_parser import kunit_kernel import kunit_json import kunit +from kunit_printer import stdout test_tmpdir = '' abs_test_data_dir = '' @@ -139,28 +140,28 @@ class KUnitParserTest(unittest.TestCase): def test_parse_successful_test_log(self): all_passed_log = test_data_path('test_is_test_passed-all_passed.log') with open(all_passed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_parse_successful_nested_tests_log(self): all_passed_log = test_data_path('test_is_test_passed-all_passed_nested.log') with open(all_passed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_kselftest_nested(self): kselftest_log = test_data_path('test_is_test_passed-kselftest.log') with open(kselftest_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual(result.counts.errors, 0) def test_parse_failed_test_log(self): failed_log = test_data_path('test_is_test_passed-failure.log') with open(failed_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.assertEqual(result.counts.errors, 0) @@ -168,7 +169,7 @@ class KUnitParserTest(unittest.TestCase): empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log') with open(empty_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests)) self.assertEqual(kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS, result.status) self.assertEqual(result.counts.errors, 1) @@ -179,7 +180,7 @@ class KUnitParserTest(unittest.TestCase): with open(missing_plan_log) as file: result = kunit_parser.parse_run_tests( kunit_parser.extract_tap_lines( - file.readlines())) + file.readlines()), stdout) # A missing test plan is not an error. self.assertEqual(result.counts, kunit_parser.TestCounts(passed=10, errors=0)) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -188,7 +189,7 @@ class KUnitParserTest(unittest.TestCase): header_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log') with open(header_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests)) self.assertEqual(kunit_parser.TestStatus.NO_TESTS, result.status) self.assertEqual(result.counts.errors, 1) @@ -197,7 +198,7 @@ class KUnitParserTest(unittest.TestCase): no_plan_log = test_data_path('test_is_test_passed-no_tests_no_plan.log') with open(no_plan_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) self.assertEqual(0, len(result.subtests[0].subtests[0].subtests)) self.assertEqual( kunit_parser.TestStatus.NO_TESTS, @@ -210,7 +211,7 @@ class KUnitParserTest(unittest.TestCase): print_mock = mock.patch('kunit_printer.Printer.print').start() with open(crash_log) as file: result = kunit_parser.parse_run_tests( - kunit_parser.extract_tap_lines(file.readlines())) + kunit_parser.extract_tap_lines(file.readlines()), stdout) print_mock.assert_any_call(StrContains('Could not find any KTAP output.')) print_mock.stop() self.assertEqual(0, len(result.subtests)) @@ -219,7 +220,7 @@ class KUnitParserTest(unittest.TestCase): def test_skipped_test(self): skipped_log = test_data_path('test_skip_tests.log') with open(skipped_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # A skipped test does not fail the whole suite. self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -228,7 +229,7 @@ class KUnitParserTest(unittest.TestCase): def test_skipped_all_tests(self): skipped_log = test_data_path('test_skip_all_tests.log') with open(skipped_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SKIPPED, result.status) self.assertEqual(result.counts, kunit_parser.TestCounts(skipped=5)) @@ -236,7 +237,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_hyphen(self): hyphen_log = test_data_path('test_strip_hyphen.log') with open(hyphen_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # A skipped test does not fail the whole suite. self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) @@ -250,7 +251,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_prefix_printk_time(self): prefix_log = test_data_path('test_config_printk_time.log') with open(prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -258,7 +259,7 @@ class KUnitParserTest(unittest.TestCase): def test_ignores_multiple_prefixes(self): prefix_log = test_data_path('test_multiple_prefixes.log') with open(prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -266,7 +267,7 @@ class KUnitParserTest(unittest.TestCase): def test_prefix_mixed_kernel_output(self): mixed_prefix_log = test_data_path('test_interrupted_tap_output.log') with open(mixed_prefix_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -274,7 +275,7 @@ class KUnitParserTest(unittest.TestCase): def test_prefix_poundsign(self): pound_log = test_data_path('test_pound_sign.log') with open(pound_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -282,7 +283,7 @@ class KUnitParserTest(unittest.TestCase): def test_kernel_panic_end(self): panic_log = test_data_path('test_kernel_panic_interrupt.log') with open(panic_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.TEST_CRASHED, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertGreaterEqual(result.counts.errors, 1) @@ -290,7 +291,7 @@ class KUnitParserTest(unittest.TestCase): def test_pound_no_prefix(self): pound_log = test_data_path('test_pound_no_prefix.log') with open(pound_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) self.assertEqual('kunit-resource-test', result.subtests[0].name) self.assertEqual(result.counts.errors, 0) @@ -310,7 +311,7 @@ class KUnitParserTest(unittest.TestCase): not ok 2 - test2 not ok 1 - some_failed_suite """ - result = kunit_parser.parse_run_tests(output.splitlines()) + result = kunit_parser.parse_run_tests(output.splitlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.assertEqual(kunit_parser._summarize_failed_tests(result), @@ -319,7 +320,7 @@ class KUnitParserTest(unittest.TestCase): def test_ktap_format(self): ktap_log = test_data_path('test_parse_ktap_output.log') with open(ktap_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) self.assertEqual(result.counts, kunit_parser.TestCounts(passed=3)) self.assertEqual('suite', result.subtests[0].name) self.assertEqual('case_1', result.subtests[0].subtests[0].name) @@ -328,13 +329,13 @@ class KUnitParserTest(unittest.TestCase): def test_parse_subtest_header(self): ktap_log = test_data_path('test_parse_subtest_header.log') with open(ktap_log) as file: - kunit_parser.parse_run_tests(file.readlines()) + kunit_parser.parse_run_tests(file.readlines(), stdout) self.print_mock.assert_any_call(StrContains('suite (1 subtest)')) def test_parse_attributes(self): ktap_log = test_data_path('test_parse_attributes.log') with open(ktap_log) as file: - result = kunit_parser.parse_run_tests(file.readlines()) + result = kunit_parser.parse_run_tests(file.readlines(), stdout) # Test should pass with no errors self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=0)) @@ -355,7 +356,7 @@ class KUnitParserTest(unittest.TestCase): Indented more. not ok 1 test1 """ - result = kunit_parser.parse_run_tests(output.splitlines()) + result = kunit_parser.parse_run_tests(output.splitlines(), stdout) self.assertEqual(kunit_parser.TestStatus.FAILURE, result.status) self.print_mock.assert_any_call(StrContains('Test output.')) @@ -544,7 +545,7 @@ class KUnitJsonTest(unittest.TestCase): def _json_for(self, log_file): with open(test_data_path(log_file)) as file: - test_result = kunit_parser.parse_run_tests(file) + test_result = kunit_parser.parse_run_tests(file, stdout) json_obj = kunit_json.get_json_result( test=test_result, metadata=kunit_json.Metadata()) @@ -810,7 +811,7 @@ class KUnitMainTest(unittest.TestCase): self.linux_source_mock.run_kernel.return_value = ['TAP version 14', 'init: random output'] + want got = kunit._list_tests(self.linux_source_mock, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'suite', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*', '', None, None, 'suite', False, False)) self.assertEqual(got, want) # Should respect the user's filter glob when listing tests. self.linux_source_mock.run_kernel.assert_called_once_with( @@ -823,7 +824,7 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*.test*', '', None, None, 'suite', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*.test*', '', None, None, 'suite', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ mock.call(args=None, build_dir='.kunit', filter_glob='suite.test*', filter='', filter_action=None, timeout=300), mock.call(args=None, build_dir='.kunit', filter_glob='suite2.test*', filter='', filter_action=None, timeout=300), @@ -836,7 +837,7 @@ class KUnitMainTest(unittest.TestCase): # Should respect the user's filter glob when listing tests. mock_tests.assert_called_once_with(mock.ANY, - kunit.KunitExecRequest(None, None, '.kunit', 300, 'suite*', '', None, None, 'test', False, False)) + kunit.KunitExecRequest(None, None, False, '.kunit', 300, 'suite*', '', None, None, 'test', False, False)) self.linux_source_mock.run_kernel.assert_has_calls([ mock.call(args=None, build_dir='.kunit', filter_glob='suite.test1', filter='', filter_action=None, timeout=300), mock.call(args=None, build_dir='.kunit', filter_glob='suite.test2', filter='', filter_action=None, timeout=300), base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc -- 2.47.0.163.g1226f6d8fa-goog

1 year

2
2
0 0

[PATCH net v2 0/2] bnxt: Fix failure to report RSS context in ntuple rule

by Daniel Xu

This patchset fixes a bug where bnxt driver was failing to report that an ntuple rule is redirecting to an RSS context. First commit is the fix, then second commit extends selftests to detect if other/new drivers are compliant with ntuple/rss_ctx API. Daniel Xu (2): bnxt_en: ethtool: Supply ntuple rss context action selftests: drv-net: rss_ctx: Add test for ntuple rule drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 8 ++++++-- tools/testing/selftests/drivers/net/hw/rss_ctx.py | 13 ++++++++++++- 2 files changed, 18 insertions(+), 3 deletions(-) -- 2.46.0

1 year

3
6
0 0

[PATCH 0/3] KVM: x86: Small changes to support VMware guests

by Zack Rusin

To be able to switch VMware products running on Linux to KVM some minor changes are required to let KVM run/resume unmodified VMware guests. First allow enabling of the VMware backdoor via an api. Currently the setting of the VMware backdoor is limited to kernel boot parameters, which forces all VM's running on a host to either run with or without the VMware backdoor. Add a simple cap to allow enabling of the VMware backdoor on a per VM basis. The default for that setting remains the kvm.enable_vmware_backdoor boot parameter (which is false by default) and can be changed on a per-vm basis via the KVM_CAP_X86_VMWARE_BACKDOOR cap. Second add a cap to forward hypercalls to userspace. I know that in general that's frowned upon but VMwre guests send quite a few hypercalls from userspace and it would be both impractical and largelly impossible to handle all in the kernel. The change is trivial and I'd be maintaining this code so I hope it's not a big deal. The third commit just adds a self-test for the "forward VMware hypercalls to userspace" functionality. Cc: Doug Covelli <doug.covelli(a)broadcom.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: x86(a)kernel.org Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Isaku Yamahata <isaku.yamahata(a)intel.com> Cc: Joel Stanley <joel(a)jms.id.au> Cc: Zack Rusin <zack.rusin(a)broadcom.com> Cc: kvm(a)vger.kernel.org Cc: linux-doc(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Zack Rusin (3): KVM: x86: Allow enabling of the vmware backdoor via a cap KVM: x86: Add support for VMware guest specific hypercalls KVM: selftests: x86: Add a test for KVM_CAP_X86_VMWARE_HYPERCALL Documentation/virt/kvm/api.rst | 56 ++++++++- arch/x86/include/asm/kvm_host.h | 2 + arch/x86/kvm/emulate.c | 5 +- arch/x86/kvm/svm/svm.c | 6 +- arch/x86/kvm/vmx/vmx.c | 4 +- arch/x86/kvm/x86.c | 47 ++++++++ arch/x86/kvm/x86.h | 7 +- include/uapi/linux/kvm.h | 2 + tools/include/uapi/linux/kvm.h | 2 + tools/testing/selftests/kvm/Makefile | 1 + .../kvm/x86_64/vmware_hypercall_test.c | 108 ++++++++++++++++++ 11 files changed, 227 insertions(+), 13 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/vmware_hypercall_test.c -- 2.43.0

1 year

4
14
0 0

[PATCH 0/5] release of KTAP version 2

by Rae Moar

This patch series represents the final release of KTAP version 2. There have been having open discussions on version 2 for just over 2 years. This patch series marks the end of KTAP version 2 development and beginning of the KTAP version 3 development. The largest component of KTAP version 2 release is the addition of test metadata to the specification. KTAP metadata could include any test information that is pertinent for user interaction before or after the running of the test. For example, the test file path or the test speed. Example of KTAP Metadata: KTAP version 2 #:ktap_test: main #:ktap_arch: uml 1..1 KTAP version 2 #:ktap_test: suite_1 #:ktap_subsystem: example #:ktap_test_file: lib/test.c 1..2 ok 1 test_1 #:ktap_test: test_2 #:ktap_speed: very_slow # test_2 has begun #:custom_is_flaky: true ok 2 test_2 # suite_1 has passed ok 1 suite_1 The release also includes some formatting fixes and changes to update the specification to version 2. Frank Rowand (2): ktap_v2: change version to 2-rc in KTAP specification ktap_v2: change "version 1" to "version 2" in examples Rae Moar (3): ktap_v2: add test metadata ktap_v2: formatting fixes to ktap spec ktap_v2: change version to 2 in KTAP specification Documentation/dev-tools/ktap.rst | 276 +++++++++++++++++++++++++++++-- 1 file changed, 260 insertions(+), 16 deletions(-) base-commit: 2d5404caa8c7bb5c4e0435f94b28834ae5456623 -- 2.47.0.277.g8800431eea-goog

1 year

1
5
0 0

[PATCH] selftests/mm: Fix unused function warning for aarch64_write_signal_pkey()

by Catalin Marinas

Since commit 49f59573e9e0 ("selftests/mm: Enable pkey_sighandler_tests on arm64"), pkey_sighandler_tests.c (which includes pkey-arm64.h via pkey-helpers.h) ends up compiled for arm64. Since it doesn't use aarch64_write_signal_pkey(), the compiler warns: In file included from pkey-helpers.h:106, from pkey_sighandler_tests.c:31: pkey-arm64.h:130:13: warning: ‘aarch64_write_signal_pkey’ defined but not used [-Wunused-function] 130 | static void aarch64_write_signal_pkey(ucontext_t *uctxt, u64 pkey) | ^~~~~~~~~~~~~~~~~~~~~~~~~ Make the aarch64_write_signal_pkey() a 'static inline void' function to avoid the compiler warning. Fixes: f5b5ea51f78f ("selftests: mm: make protection_keys test work on arm64") Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: Joey Gouly <joey.gouly(a)arm.com> Cc: Kevin Brodsky <kevin.brodsky(a)arm.com> Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> --- I'll add this on top of the arm64 for-next/pkey-signal branch together with Kevin's other patches. tools/testing/selftests/mm/pkey-arm64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h index d57fbeace38f..d9d2100eafc0 100644 --- a/tools/testing/selftests/mm/pkey-arm64.h +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -127,7 +127,7 @@ static inline u64 get_pkey_bits(u64 reg, int pkey) return 0; } -static void aarch64_write_signal_pkey(ucontext_t *uctxt, u64 pkey) +static inline void aarch64_write_signal_pkey(ucontext_t *uctxt, u64 pkey) { struct _aarch64_ctx *ctx = GET_UC_RESV_HEAD(uctxt); struct poe_context *poe_ctx =

1 year

2
2
0 0

[PATCH 0/4] kselftest/arm64: Fix compilation warnings/errors in the arm64 tests

by Catalin Marinas

It looks like people started ignoring the compiler warnings (or even errors) when building the arm64-specific kselftests. The first three patches are printf() arguments adjustment. The last one adds ".arch_extension sme", otherwise they fail to build (with my toolchain versions at least). Note for future kselftest contributors - try to keep them warning-free. Catalin Marinas (4): kselftest/arm64: Fix printf() compiler warnings in the arm64 fp tests kselftest/arm64: Fix printf() warning in the arm64 MTE prctl() test kselftest/arm64: Fix printf() compiler warnings in the arm64 syscall-abi.c tests kselftest/arm64: Fix compilation of SME instructions in the arm64 fp tests tools/testing/selftests/arm64/abi/syscall-abi.c | 8 ++++---- tools/testing/selftests/arm64/fp/sve-ptrace.c | 16 +++++++++------- tools/testing/selftests/arm64/fp/za-ptrace.c | 8 +++++--- tools/testing/selftests/arm64/fp/za-test.S | 1 + tools/testing/selftests/arm64/fp/zt-ptrace.c | 8 +++++--- tools/testing/selftests/arm64/fp/zt-test.S | 1 + tools/testing/selftests/arm64/mte/check_prctl.c | 2 +- 7 files changed, 26 insertions(+), 18 deletions(-)

1 year

2
16
0 0

[PATCH v2 0/6] kselftest/arm64: Test floating point signal context restore in fp-stress

by Mark Brown

Currently we test signal delivery to the programs run by fp-stress but our signal handlers simply count the number of signals seen and don't do anything with the floating point state. The original fpsimd-test and sve-test programs had signal handlers called irritators which modify the live register state, verifying that we restore the signal context on return, but a combination of misleading comments and code resulted in them never being used and the equivalent handlers in the other tests being stubbed or omitted. Clarify the code, implement effective irritator handlers for the test programs that can have them and then switch the signals generated by the fp-stress program over to use the irritators, ensuring that we validate that we restore the saved signal context properly. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Change instruction and commit log for corruption of predicat registers. - Link to v1: https://lore.kernel.org/r/20241023-arm64-fp-stress-irritator-v1-0-a51af298d… --- Mark Brown (6): kselftest/arm64: Correct misleading comments on fp-stress irritators kselftest/arm64: Remove unused ADRs from irritator handlers kselftest/arm64: Corrupt P0 in the irritator when testing SSVE kselftest/arm64: Implement irritators for ZA and ZT kselftest/arm64: Provide a SIGUSR1 handler in the kernel mode FP stress test kselftest/arm64: Test signal handler state modification in fp-stress tools/testing/selftests/arm64/fp/fp-stress.c | 2 +- tools/testing/selftests/arm64/fp/fpsimd-test.S | 4 +--- tools/testing/selftests/arm64/fp/kernel-test.c | 4 ++++ tools/testing/selftests/arm64/fp/sve-test.S | 8 +++----- tools/testing/selftests/arm64/fp/za-test.S | 13 ++++--------- tools/testing/selftests/arm64/fp/zt-test.S | 13 ++++--------- 6 files changed, 17 insertions(+), 27 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241023-arm64-fp-stress-irritator-5415fe92adef Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
8
0 0

[PATCH v2 0/3] kselftest/arm64: fp-ptrace enhancements

by Mark Brown

This series contains a bit of a grab bag of improvements to the floating point tests, mainly fp-ptrace. Globally over all the tests we start using defines from the generated sysregs (following the example of the KVM selftests) for SVCR, stop being quite so wasteful with registers when calling into the assembler code then expand the coverage of both ZA writes and FPMR (which was not there since fp-ptrace and the 2023 dpISA extensions were on the list at the same time). Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Drop attempt to reference sysreg-defs.h due to build issues, just import the defines directly into fp-ptrace. We can revisit later. - Link to v1: https://lore.kernel.org/r/20241107-arm64-fp-ptrace-fpmr-v1-0-3e5e0b6e3be9@k… --- Mark Brown (3): kselftets/arm64: Use flag bits for features in fp-ptrace assembler code kselftest/arm64: Expand the set of ZA writes fp-ptrace does kselftest/arm64: Add FPMR coverage to fp-ptrace tools/testing/selftests/arm64/fp/fp-ptrace-asm.S | 41 ++++-- tools/testing/selftests/arm64/fp/fp-ptrace.c | 161 +++++++++++++++++++++-- tools/testing/selftests/arm64/fp/fp-ptrace.h | 12 ++ tools/testing/selftests/arm64/fp/sme-inst.h | 2 + 4 files changed, 188 insertions(+), 28 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241105-arm64-fp-ptrace-fpmr-ff061facd3da Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
6
0 0

[PATCH] kselftest/arm64: Fix build with stricter assemblers

by Mark Brown

While some assemblers (including the LLVM assembler I mostly use) will happily accept SMSTART as an instruction by default others, specifically gas, require that any architecture extensions be explicitly enabled. The assembler SME test programs use manually encoded helpers for the new instructions but no SMSTART helper is defined, only SM and ZA specific variants. Unfortunately the irritators that were just added use plain SMSTART so on stricter assemblers these fail to build: za-test.S:160: Error: selected processor does not support `smstart' Switch to using SMSTART ZA via the manually encoded smstart_za macro we already have defined. Fixes: d65f27d240bb ("kselftest/arm64: Implement irritators for ZA and ZT") Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/fp/za-test.S | 2 +- tools/testing/selftests/arm64/fp/zt-test.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S index 95fdc1c1f228221bc812087a528e4b7c99767bba..9c33e13e9dc4a6f084649fe7d0fb838d9171e3aa 100644 --- a/tools/testing/selftests/arm64/fp/za-test.S +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -157,7 +157,7 @@ function irritator_handler // This will reset ZA to all bits 0 smstop - smstart + smstart_za ret endfunction diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S index a90712802801efb97dc6bf8027fb9ceac8f0a895..38080f3c328042af6b3e2d7c3300162ea6efa4ea 100644 --- a/tools/testing/selftests/arm64/fp/zt-test.S +++ b/tools/testing/selftests/arm64/fp/zt-test.S @@ -126,7 +126,7 @@ function irritator_handler // This will reset ZT to all bits 0 smstop - smstart + smstart_za ret endfunction --- base-commit: 95ad089d464da2a4cd4511fb077f25994104c8f1 change-id: 20241108-arm64-selftest-asm-error-d78570e50b3b Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
4
0 0

[PATCH] kselftest/arm64: Enable build of PAC tests with LLVM=1

by Mark Brown

Currently we don't build the PAC selftests when building with LLVM=1 since we attempt to test for PAC support in the toolchain before we've set up the build system to point at LLVM in lib.mk, which has to be one of the last things in the Makefile. Since all versions of LLVM supported for use with the kernel have PAC support we can just sidestep the issue by just assuming PAC is there when doing a LLVM=1 build. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/pauth/Makefile | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/arm64/pauth/Makefile b/tools/testing/selftests/arm64/pauth/Makefile index 72e290b0b10c1ea5bf1b84232f70844a601b8129..b5a1c80e0ead6932d2441a192b9758a049e3b3f8 100644 --- a/tools/testing/selftests/arm64/pauth/Makefile +++ b/tools/testing/selftests/arm64/pauth/Makefile @@ -7,8 +7,14 @@ CC := $(CROSS_COMPILE)gcc endif CFLAGS += -mbranch-protection=pac-ret + +# All supported LLVMs have PAC, test for GCC +ifeq ($(LLVM),1) +pauth_cc_support := 1 +else # check if the compiler supports ARMv8.3 and branch protection with PAuth pauth_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.3-a -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi) +endif ifeq ($(pauth_cc_support),1) TEST_GEN_PROGS := pac --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241111-arm64-selftest-pac-clang-cb80de079169 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
1
0 0

[PATCH] kselftest/arm64: Check that SVCR is 0 in signal handlers

by Mark Brown

We don't currently validate that we exit streaming mode and clear ZA when we enter a signal handler. Add simple checks for this in the SSVE and ZA tests. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/signal/sve_helpers.h | 13 +++++++++++++ tools/testing/selftests/arm64/signal/testcases/ssve_regs.c | 5 +++++ tools/testing/selftests/arm64/signal/testcases/za_regs.c | 5 +++++ 3 files changed, 23 insertions(+) diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.h b/tools/testing/selftests/arm64/signal/sve_helpers.h index 50948ce471cc620118a0c7c8df70d66dbdfbb160..ca133b93375fa587b5e02cd76b2f2fcd92591723 100644 --- a/tools/testing/selftests/arm64/signal/sve_helpers.h +++ b/tools/testing/selftests/arm64/signal/sve_helpers.h @@ -18,4 +18,17 @@ extern unsigned int nvls; int sve_fill_vls(bool use_sme, int min_vls); +static inline uint64_t get_svcr(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, S3_3_C4_C2_2\n" + : "=r"(val) + : + : "cc"); + + return val; +} + #endif diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c index 6dbe48cf8b09ed8b7a5ab47690bd87e39e18e1e6..3dee68fa36d1cf2716f54d5f328b3f4077493c3b 100644 --- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -85,6 +85,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, fprintf(stderr, "Got expected size %u and VL %d\n", head->size, ssve->vl); + if (get_svcr() != 0) { + fprintf(stderr, "Unexpected SVCR %llx\n", get_svcr()); + return 1; + } + return 0; } diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c index b9e13f27f1f9aaf55db2a5e391f360993561d0b7..9fff4c50030414d06157e0da0c29fd794f707309 100644 --- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c @@ -91,6 +91,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, return 1; } + if (get_svcr() != 0) { + fprintf(stderr, "Unexpected SVCR %llx\n", get_svcr()); + return 1; + } + return 0; } --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241106-arm64-fpmr-signal-test-c0a0c5bf0174 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
3
0 0

[PATCH 0/2] kselftest/arm64: Avoid detecting spurious PAC key collisions

by Mark Brown

The PAC tests currently generate a very small number of false failures since the limited size of PAC keys, especially with fewer bits allocated for PAC due to larger VA, means collisions in generated PACs are possible even if the PAC keys are different. The test tries to work around this by testing repeatedly but doesn't iterate often enough to be reliable. We also fix a leak of file descriptors in the exec test which doesn't matter now but can become an issue when the number of iterations is increased, we can bump into limits on allocated file descriptors. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (2): kselftest/arm64: Don't leak pipe fds in pac.exec_sign_all() kselftest/arm64: Try harder to generate different keys during PAC tests tools/testing/selftests/arm64/pauth/pac.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241111-arm64-pac-test-collisions-5613f5dfe479 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
3
0 0

[PATCH 0/4] kselftest/arm64: fp-ptrace enhancements

by Mark Brown

This series contains a bit of a grab bag of improvements to the floating point tests, mainly fp-ptrace. Globally over all the tests we start using defines from the generated sysregs (following the example of the KVM selftests) for SVCR, stop being quite so wasteful with registers when calling into the assembler code then expand the coverage of both ZA writes and FPMR (which was not there since fp-ptrace and the 2023 dpISA extensions were on the list at the same time). Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (4): kselftets/arm64: Use flag bits for features in fp-ptrace assembler code kselftest/arm64: Use a define for SVCR kselftest/arm64: Expand the set of ZA writes fp-ptrace does kselftest/arm64: Add FPMR coverage to fp-ptrace tools/testing/selftests/arm64/fp/Makefile | 20 ++- tools/testing/selftests/arm64/fp/fp-ptrace-asm.S | 52 +++++--- tools/testing/selftests/arm64/fp/fp-ptrace.c | 155 +++++++++++++++++++++-- tools/testing/selftests/arm64/fp/fp-ptrace.h | 16 ++- tools/testing/selftests/arm64/fp/sve-test.S | 5 +- tools/testing/selftests/arm64/fp/za-fork-asm.S | 3 +- tools/testing/selftests/arm64/fp/za-test.S | 6 +- tools/testing/selftests/arm64/fp/zt-test.S | 5 +- 8 files changed, 213 insertions(+), 49 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241105-arm64-fp-ptrace-fpmr-ff061facd3da Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
6
0 0

[PATCH] kunit: skb: add gfp to kernel doc for kunit_zalloc_skb()

by Dan Carpenter

Kuan-Wei Chiu pointed out that the kernel doc for kunit_zalloc_skb() needs to include the @gfp information. Add it. Reported-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Closes: https://lore.kernel.org/all/Zy+VIXDPuU613fFd@visitorckw-System-Product-Name/ Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> --- include/kunit/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/kunit/skbuff.h b/include/kunit/skbuff.h index 345e1e8f0312..07784694357c 100644 --- a/include/kunit/skbuff.h +++ b/include/kunit/skbuff.h @@ -20,8 +20,9 @@ static void kunit_action_kfree_skb(void *p) * kunit_zalloc_skb() - Allocate and initialize a resource managed skb. * @test: The test case to which the skb belongs * @len: size to allocate + * @gfp: allocation flags * - * Allocate a new struct sk_buff with GFP_KERNEL, zero fill the give length + * Allocate a new struct sk_buff with gfp flags, zero fill the given length * and add it as a resource to the kunit test for automatic cleanup. * * Returns: newly allocated SKB, or %NULL on error -- 2.45.2

1 year

3
2
0 0

[PATCH net-next v2 0/8] net: Improve netns handling in RTNL and ip_tunnel

by Xiao Liang

This patch series includes some netns-related improvements and fixes for RTNL and ip_tunnel, to make link creation more intuitive: - Creating link in another net namespace doesn't conflict with link names in current one. - Add a flag in rtnl_ops, to avoid netns change when link-netns is present if possible. - When creating ip tunnel (e.g. GRE) in another netns, use current as link-netns if not specified explicitly. So that # modprobe ip_gre netns_atomic=1 # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. --- v2: - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Xiao Liang (8): rtnetlink: Lookup device in target netns when creating link rtnetlink: Add netns_atomic flag in rtnl_link_ops net: ip_tunnel: Build flow in underlay net namespace net: ip_tunnel: Add source netns support for newlink net: ip_gre: Add netns_atomic module parameter net: dummy: Set netns_atomic in rtnl ops for testing tools/net/ynl: Add retry limit for async notification selftests: net: Add two test cases for link netns drivers/net/dummy.c | 1 + include/net/ip_tunnels.h | 3 ++ include/net/rtnetlink.h | 3 ++ net/core/rtnetlink.c | 17 +++++-- net/ipv4/ip_gre.c | 15 +++++- net/ipv4/ip_tunnel.c | 27 +++++++---- tools/net/ynl/lib/ynl.py | 7 ++- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/netns-name.sh | 10 ++++ tools/testing/selftests/net/netns_atomic.py | 54 +++++++++++++++++++++ 10 files changed, 121 insertions(+), 17 deletions(-) create mode 100755 tools/testing/selftests/net/netns_atomic.py -- 2.47.0

1 year

4
25
0 0

[PATCH net-next v10] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- V10: selfttests in pmtu.sh: - remove unused fail var - Flip error messages V9: selftests in pmtu.sh: - remove useless return - fix mtu var override V8: selftests in pmtu.sh: - Change var names from "dummy" to "host" - Fix errors caused by incorrect iface arguments pass - Add src addr to setup_multipath_new - Change multipath* func order - Change route_get_dst_exception() && route_get_dst_pmtu_from_exception() and arguments pass where they are used as Ido suggested in https://lore.kernel.org/all/ZykH_fdcMBdFgXix@shredder/ V7: selftest in pmtu.sh: - add setup_multipath() with old and new nh tests - add global "dummy_v4" addr variables - add documentation - remove dummy netdev usage in mp nh test - remove useless sysctl opts in mp nh test V6: - make commit message cleaner V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - add selftest - fix compile error V2: - fix fib_info_num_path parameter pass --- net/ipv4/route.c | 13 ++++ tools/testing/selftests/net/pmtu.sh | 112 +++++++++++++++++++++++----- 2 files changed, 108 insertions(+), 17 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..652f603d29fe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..7ca2fbd971ae 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -197,6 +197,12 @@ # # - pmtu_ipv6_route_change # Same as above but with IPv6 +# +# - pmtu_ipv4_mp_exceptions +# Use the same topology as in pmtu_ipv4, but add routeable addresses +# on host A and B on lo reachable via both routers. Host A and B +# addresses have multipath routes to each other, b_r1 mtu = 1500. +# Check that PMTU exceptions are created for both paths. source lib.sh source net_helper.sh @@ -266,7 +272,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 1" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a" tunnel6_b_addr="fd00:2::b" tunnel6_mask="64" +host4_a_addr="192.168.99.99" +host4_b_addr="192.168.88.88" + dummy6_0_prefix="fc00:1000::" dummy6_1_prefix="fc00:1001::" dummy6_mask="64" @@ -984,6 +994,52 @@ setup_ovs_bridge() { run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 } +setup_multipath_new() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip nexthop add id 401 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 402 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 403 group 401/402 + run_cmd ${ns_a} ip route add ${host4_b_addr} src ${host4_a_addr} nhid 403 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip nexthop add id 401 via ${prefix4}.${b_r1}.2 dev veth_B-R1 + run_cmd ${ns_b} ip nexthop add id 402 via ${prefix4}.${b_r2}.2 dev veth_B-R2 + run_cmd ${ns_b} ip nexthop add id 403 group 401/402 + run_cmd ${ns_b} ip route add ${host4_a_addr} src ${host4_b_addr} nhid 403 +} + +setup_multipath_old() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip route add ${host4_b_addr} \ + src ${host4_a_addr} \ + nexthop via ${prefix4}.${a_r1}.2 weight 1 \ + nexthop via ${prefix4}.${a_r2}.2 weight 1 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip route add ${host4_a_addr} \ + src ${host4_b_addr} \ + nexthop via ${prefix4}.${b_r1}.2 weight 1 \ + nexthop via ${prefix4}.${b_r2}.2 weight 1 +} + +setup_multipath() { + if [ "$USE_NH" = "yes" ]; then + setup_multipath_new + else + setup_multipath_old + fi + + # Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${host4_a_addr} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_a_addr} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${host4_b_addr} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_b_addr} via ${prefix4}.${b_r2}.1 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -1076,23 +1132,15 @@ link_get_mtu() { } route_get_dst_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - if [ -z "${dsfield}" ]; then - dsfield=0 - fi - - ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" + ${ns_cmd} ip route get "$@" } route_get_dst_pmtu_from_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "$@")" } check_pmtu_value() { @@ -1235,10 +1283,10 @@ test_pmtu_ipv4_dscp_icmp_exception() { run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -1285,9 +1333,9 @@ test_pmtu_ipv4_dscp_udp_exception() { UDP:"${dst2}":50000,tos="${dsfield}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -2329,6 +2377,36 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing multipath || return $ksft_skip + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + # Ping and expect two nexthop exceptions for two routes + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${host4_b_addr}" + + # Check that exceptions have been created with the correct PMTU + pmtu_a_R1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R1)" + pmtu_a_R2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R2)" + + check_pmtu_value "1500" "${pmtu_a_R1}" "exceeding MTU (veth_A-R1)" || return 1 + check_pmtu_value "1500" "${pmtu_a_R2}" "exceeding MTU (veth_A-R2)" || return 1 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year

3
2
0 0

[PATCH net-next] net: netconsole: selftests: Check if netdevsim is available

by Breno Leitao

The netconsole selftest relies on the availability of the netdevsim module. To ensure the test can run correctly, we need to check if the netdevsim module is either loaded or built-in before proceeding. Update the netconsole selftest to check for the existence of the /sys/bus/netdevsim/new_device file before running the test. If the file is not found, the test is skipped with an explanation that the CONFIG_NETDEVSIM kernel config option may not be enabled. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- tools/testing/selftests/drivers/net/netcons_basic.sh | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index 182eb1a97e59f3b4c9eea0e5b9e64a7fff656e2b..b175f4d966e5056ddb62e335f212c03e55f50fb0 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -39,6 +39,7 @@ NAMESPACE="" # IDs for netdevsim NSIM_DEV_1_ID=$((256 + RANDOM % 256)) NSIM_DEV_2_ID=$((512 + RANDOM % 256)) +NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" # Used to create and delete namespaces source "${SCRIPTDIR}"/../../net/lib.sh @@ -46,7 +47,6 @@ source "${SCRIPTDIR}"/../../net/net_helper.sh # Create netdevsim interfaces create_ifaces() { - local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" @@ -212,6 +212,11 @@ function check_for_dependencies() { exit "${ksft_skip}" fi + if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then + echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 + exit "${ksft_skip}" + fi + if [ ! -d "${NETCONS_CONFIGFS}" ]; then echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 exit "${ksft_skip}" --- base-commit: 4861333b42178fa3d8fd1bb4e2cfb2fedc968dba change-id: 20241108-netcon_selftest_deps-83f26456f095 Best regards, -- Breno Leitao <leitao(a)debian.org>

1 year

3
2
0 0

[PATCH net-next v9 0/6] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v9, see changelog below. This revision addresses feedback Willem gave on the selftests. No functional or code changes to the implementation were made and performance tests were not re-run. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Important call out in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspend0: - set defer_hard_irqs to 0 - set gro_flush_timeout to 0 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over nearly 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results shift between submissions, but the relative differences are equivalent. As patches are rebased, several factors likely influence overall performance. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. - suspend0, which sets defer_hard_irqs and gro_flush_timeout to 0, has nearly the same performance as the base case (this is FAQ item #1). The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 199946 112 239 416 26 12973 11343 defer10 200K 199971 54 124 142 29 19412 17460 defer20 200K 199986 60 130 153 26 15644 14095 defer50 200K 200025 79 144 182 23 12122 11632 defer200 200K 199999 164 254 309 19 8923 9635 fullbusy 200K 199998 46 118 133 100 43658 23133 napibusy 200K 199983 100 237 277 56 24840 24716 suspend0 200K 200020 105 249 432 30 14264 11796 suspend10 200K 199950 53 123 141 32 19518 16903 suspend20 200K 200037 58 126 151 30 16426 14736 suspend50 200K 199961 73 136 177 26 13310 12633 suspend200 200K 199998 149 251 306 21 9566 10203 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400014 139 269 707 41 9476 9343 defer10 400K 400016 59 133 166 53 13991 12989 defer20 400K 399952 67 140 172 47 12063 11644 defer50 400K 400007 87 162 198 39 9384 9880 defer200 400K 399979 181 274 330 31 7089 8430 fullbusy 400K 399987 50 123 156 100 21827 16037 napibusy 400K 400014 76 222 272 83 18185 16529 suspend0 400K 400015 127 350 776 47 10699 9603 suspend10 400K 400023 57 129 164 54 13758 13178 suspend20 400K 400043 62 135 169 49 12071 11826 suspend50 400K 400071 76 149 186 42 10011 10301 suspend200 400K 399961 154 269 327 34 7827 8774 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 599951 149 266 574 61 9265 8876 defer10 600K 600006 71 147 203 76 11866 10936 defer20 600K 600123 76 152 203 66 10430 10342 defer50 600K 600162 95 172 217 54 8526 9142 defer200 600K 599942 200 301 357 46 6977 8212 fullbusy 600K 599990 55 127 177 100 14551 13983 napibusy 600K 600035 63 160 250 96 13937 14140 suspend0 600K 599903 127 320 732 68 10166 8963 suspend10 600K 599908 63 137 192 69 10902 11100 suspend20 600K 599961 66 141 194 65 9976 10370 suspend50 600K 599973 80 159 204 57 8678 9381 suspend200 600K 600010 157 277 346 48 7133 8381 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800039 181 300 536 87 9585 8304 defer10 800K 800038 181 530 939 96 10564 8970 defer20 800K 800029 112 225 329 90 10056 8935 defer50 800K 799999 120 208 296 82 9234 8562 defer200 800K 800066 227 338 401 63 7117 8129 fullbusy 800K 800040 61 134 190 100 10913 12608 napibusy 800K 799944 64 141 214 99 10828 12588 suspend0 800K 799911 126 248 509 85 9346 8498 suspend10 800K 800006 69 143 200 83 9410 9845 suspend20 800K 800120 74 150 207 78 8786 9454 suspend50 800K 799989 87 168 224 71 7946 8833 suspend200 800K 799987 160 292 357 62 6923 8229 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 906879 4079 5751 6216 98 9496 7904 defer10 1000K 860849 3643 6274 6730 99 10040 8676 defer20 1000K 896063 3298 5840 6349 98 9620 8237 defer50 1000K 919782 2962 5513 5807 97 9284 7951 defer200 1000K 970941 3059 5348 5984 95 8593 7959 fullbusy 1000K 999950 70 150 207 100 8732 10777 napibusy 1000K 999996 78 154 223 100 8722 10656 suspend0 1000K 949706 2666 5770 6660 99 9071 8046 suspend10 1000K 1000024 80 160 220 92 8137 9035 suspend20 1000K 1000059 83 165 226 89 7850 8804 suspend50 1000K 999955 95 180 240 84 7411 8459 suspend200 1000K 999914 163 299 366 77 6833 8078 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1037654 4184 5453 5810 100 8411 7938 defer10 MAX 905607 4840 6151 6380 100 9639 8431 defer20 MAX 986463 4455 5594 5796 100 8848 8110 defer50 MAX 1077030 4000 5073 5299 100 8104 7920 defer200 MAX 1040728 4152 5385 5765 100 8379 7849 fullbusy MAX 1247536 3518 3935 3984 100 6998 7930 napibusy MAX 1136310 3799 7756 9964 100 7670 7877 suspend0 MAX 1057509 4132 5724 6185 100 8253 7918 suspend10 MAX 1215147 3580 3957 4041 100 7185 7944 suspend20 MAX 1216469 3576 3953 3988 100 7175 7950 suspend50 MAX 1215871 3577 3961 4075 100 7181 7949 suspend200 MAX 1216882 3556 3951 3988 100 7175 7955 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2 can take control from Loop 1, if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2 and 3 "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2, which essentially tilts this in favour of Loop 3. If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3 cannot take control from Loop 1. Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. This is shown in the results above: compare suspend0 with the base case. Note that the lack of napi_defer_hard_irqs and gro_flush_timeout produce similar results for both, which encourages the use of napi_defer_hard_irqs and gro_flush_timeout in addition to irq_suspend_timeout. - Can the new timeout value be threaded through the new epoll ioctl ? It is possible, but presents challenges for userspace. User applications must ensure that the file descriptors added to epoll contexts have the same NAPI ID to support busy polling. An epoll context is not permanently tied to any particular NAPI ID. So, a user application could decide to clear the file descriptors from the context and add a new set of file descriptors with a different NAPI ID to the context. Busy polling would work as expected, but the meaning of the suspend timeout becomes ambiguous because IRQs are not inherently associated with epoll contexts, but rather with the NAPI. The user program would need to reissue the ioctl to set the irq_suspend_timeout, but the napi_defer_hard_irqs and gro_flush_timeout settings would come from the NAPI's napi_config (which are set either by sysfs or by netlink). Such an interface seems awkard to use from a user perspective. Further, IRQs are related to NAPIs, which is why they are stored in the napi_config space. Putting the irq_suspend_timeout in the epoll context while other IRQ deferral mechanisms remain in the NAPI's napi_config space seems like an odd design choice. We've opted to keep all of the IRQ deferral parameters together and place the irq_suspend_timeout in napi_config. This has nice benefits for userspace: if a user app were to remove all file descriptors from an epoll context and add new file descriptors with a new NAPI ID, the correct suspend timeout for that NAPI ID would be used automatically without the user application needing to do anything (like re-issuing an ioctl, for example). All IRQ deferral related parameters are in one place and can all be set the same way: with netlink. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the results. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v9: - Addresses Willem's feedback on the selftests in patch 5 by fixing the SPDX-License-Identifier, moving constants into variables in the test script, reducing code duplication, shortening long lines, and renaming variables to be more reader friendly. In the C test file, added a comment explaining the if def blob and changed a few types for strtoul. v8: https://lore.kernel.org/netdev/20241108045337.292905-1-jdamato@fastly.com/ - Update patch 2 to drop the exports, as requested by Jakub. v7: https://lore.kernel.org/netdev/20241108023912.98416-1-jdamato@fastly.com/ - Jakub noted that patch 2 adds unnecessary complexity by checking the suspend timeout in the NAPI loop. This makes the code more complicated and difficult to reason about. He's right; we've dropped patch 2 which simplifies this series. - Updated the cover letter with a full re-run of all test cases. - Updated FAQ #2. v6: https://lore.kernel.org/netdev/20241104215542.215919-1-jdamato@fastly.com/ - Updated the cover letter with a full re-run of all test cases, including a new case suspend0, as requested by Sridhar previously. - Updated the kernel documentation in patch 7 as suggested by Bagas Sanjaya, which improved the htmldoc output. v5: https://lore.kernel.org/netdev/20241103052421.518856-1-jdamato@fastly.com/ - Adjusted patch 5 to only suspend IRQs when ep_send_events returns a positive return value. This issue was pointed out by Hillf Danton. - Updated the commit message of patch 6 which still mentioned netcat, despite the code being updated in v4 to replace it with socat and fixed misspelling of netdevsim. - Fixed a minor typo in patch 7 and removed an unnecessary paragraph. - Added Sridhar Samudrala's Reviewed-by to patch 1-5 and 7. v4: https://lore.kernel.org/netdev/20241102005214.32443-1-jdamato@fastly.com/ - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: https://lore.kernel.org/netdev/20241101004846.32532-1-jdamato@fastly.com/ - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (4): net: Add napi_struct parameter irq_suspend_timeout net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 170 ++++++++- fs/eventpoll.c | 36 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 39 ++ net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 165 +++++++++ tools/testing/selftests/net/busy_poller.c | 346 ++++++++++++++++++ 15 files changed, 809 insertions(+), 7 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dc7c381bb8649e3701ed64f6c3e55316675904d7 -- 2.25.1

1 year

3
3
0 0

[PATCH net-next v8 00/12] selftests: ncdevmem: Add ncdevmem to ksft

by Stanislav Fomichev

The goal of the series is to simplify and make it possible to use ncdevmem in an automated way from the ksft python wrapper. ncdevmem is slowly mutated into a state where it uses stdout to print the payload and the python wrapper is added to make sure the arrived payload matches the expected one. v8: - move error() calls into enable_reuseaddr() (Joe) - bail out when number of queues is 1 (Joe) - use socat instead of nc (Joe) - fix warning about string truncation buf[256]->buf[40] (Jakub) v7: - fix validation (Mina) - add support for working with non ::ffff-prefixed addresses (Mina) v6: - fix compilation issue in 'Unify error handling' patch (Jakub) v5: - properly handle errors from inet_pton() and socket() (Paolo) - remove unneeded import from python selftest (Paolo) v4: - keep usage example with validation (Mina) - fix compilation issue in one patch (s/start_queues/start_queue/) v3: - keep and refine the comment about ncdevmem invocation (Mina) - add the comment about not enforcing exit status for ntuple reset (Mina) - make configure_headersplit more robust (Mina) - use num_queues/2 in selftest and let the users override it (Mina) - remove memory_provider.memcpy_to_device (Mina) - keep ksft as is (don't use -v validate flags): we are gonna need a --debug-disable flag to make it less chatty; otherwise it times out when sending too much data; so leaving it as a separate follow up v2: - don't remove validation (Mina) - keep 5-tuple flow steering but use it only when -c is provided (Mina) - remove separate flag for probing (Mina) - move ncdevmem under drivers/net/hw, not drivers/net (Jakub) Cc: Mina Almasry <almasrymina(a)google.com> Stanislav Fomichev (12): selftests: ncdevmem: Redirect all non-payload output to stderr selftests: ncdevmem: Separate out dmabuf provider selftests: ncdevmem: Unify error handling selftests: ncdevmem: Make client_ip optional selftests: ncdevmem: Remove default arguments selftests: ncdevmem: Switch to AF_INET6 selftests: ncdevmem: Properly reset flow steering selftests: ncdevmem: Use YNL to enable TCP header split selftests: ncdevmem: Remove hard-coded queue numbers selftests: ncdevmem: Run selftest when none of the -s or -c has been provided selftests: ncdevmem: Move ncdevmem under drivers/net/hw selftests: ncdevmem: Add automated test .../selftests/drivers/net/hw/.gitignore | 1 + .../testing/selftests/drivers/net/hw/Makefile | 9 + .../selftests/drivers/net/hw/devmem.py | 45 + .../selftests/drivers/net/hw/ncdevmem.c | 789 ++++++++++++++++++ tools/testing/selftests/net/.gitignore | 1 - tools/testing/selftests/net/Makefile | 8 - tools/testing/selftests/net/ncdevmem.c | 570 ------------- 7 files changed, 844 insertions(+), 579 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/.gitignore create mode 100755 tools/testing/selftests/drivers/net/hw/devmem.py create mode 100644 tools/testing/selftests/drivers/net/hw/ncdevmem.c delete mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.47.0

1 year

4
16
0 0

[PATCH net-next v3 0/4] Introduce VLAN support in HSR

by MD Danish Anwar

This series adds VLAN support to HSR framework. This series also adds VLAN support to HSR mode of ICSSG Ethernet driver. Changes from v2 to v3: *) Modified hsr_ndo_vlan_rx_add_vid() to handle arbitrary HSR_PT_SLAVE_A, HSR_PT_SLAVE_B order and skip INTERLINK port in patch 2/4 as suggested by Paolo Abeni <pabeni(a)redhat.com> *) Removed handling of HSR_PT_MASTER in hsr_ndo_vlan_rx_kill_vid() as MASTER and INTERLINK port will be ignored anyway in the default switch case as suggested by Paolo Abeni <pabeni(a)redhat.com> *) Modified the selftest in patch 4/4 to use vlan by default. The test will check the exposed feature `vlan-challenged` and if vlan is not supported, skip the vlan test as suggested by Paolo Abeni <pabeni(a)redhat.com>. Test logs can be found at [1] Changes from v1 to v2: *) Added patch 4/4 to add test script related to VLAN in HSR as asked by Lukasz Majewski <lukma(a)denx.de> [1] https://gist.githubusercontent.com/danish-ti/d309f92c640134ccc4f2c0c442de5b… v1 https://lore.kernel.org/all/20241004074715.791191-1-danishanwar@ti.com/ v2 https://lore.kernel.org/all/20241024103056.3201071-1-danishanwar@ti.com/ MD Danish Anwar (1): selftests: hsr: Add test for VLAN Murali Karicheri (1): net: hsr: Add VLAN CTAG filter support Ravi Gunasekaran (1): net: ti: icssg-prueth: Add VLAN support for HSR mode WingMan Kwok (1): net: hsr: Add VLAN support drivers/net/ethernet/ti/icssg/icssg_prueth.c | 45 ++++++++- net/hsr/hsr_device.c | 85 +++++++++++++++-- net/hsr/hsr_forward.c | 19 +++- tools/testing/selftests/net/hsr/config | 1 + tools/testing/selftests/net/hsr/hsr_ping.sh | 98 ++++++++++++++++++++ 5 files changed, 236 insertions(+), 12 deletions(-) base-commit: a84e8c05f58305dfa808bc5465c5175c29d7c9b6 -- 2.34.1

1 year

3
6
0 0

[PATCH net-next v7] ipv6: Fix soft lockups in fib6_select_path under high next hop churn

by Omid Ehtemam-Haghighi

Soft lockups have been observed on a cluster of Linux-based edge routers located in a highly dynamic environment. Using the `bird` service, these routers continuously update BGP-advertised routes due to frequently changing nexthop destinations, while also managing significant IPv6 traffic. The lockups occur during the traversal of the multipath circular linked-list in the `fib6_select_path` function, particularly while iterating through the siblings in the list. The issue typically arises when the nodes of the linked list are unexpectedly deleted concurrently on a different core—indicated by their 'next' and 'previous' elements pointing back to the node itself and their reference count dropping to zero. This results in an infinite loop, leading to a soft lockup that triggers a system panic via the watchdog timer. Apply RCU primitives in the problematic code sections to resolve the issue. Where necessary, update the references to fib6_siblings to annotate or use the RCU APIs. Include a test script that reproduces the issue. The script periodically updates the routing table while generating a heavy load of outgoing IPv6 traffic through multiple iperf3 clients. It consistently induces infinite soft lockups within a couple of minutes. Kernel log: 0 [ffffbd13003e8d30] machine_kexec at ffffffff8ceaf3eb 1 [ffffbd13003e8d90] __crash_kexec at ffffffff8d0120e3 2 [ffffbd13003e8e58] panic at ffffffff8cef65d4 3 [ffffbd13003e8ed8] watchdog_timer_fn at ffffffff8d05cb03 4 [ffffbd13003e8f08] __hrtimer_run_queues at ffffffff8cfec62f 5 [ffffbd13003e8f70] hrtimer_interrupt at ffffffff8cfed756 6 [ffffbd13003e8fd0] __sysvec_apic_timer_interrupt at ffffffff8cea01af 7 [ffffbd13003e8ff0] sysvec_apic_timer_interrupt at ffffffff8df1b83d -- <IRQ stack> -- 8 [ffffbd13003d3708] asm_sysvec_apic_timer_interrupt at ffffffff8e000ecb [exception RIP: fib6_select_path+299] RIP: ffffffff8ddafe7b RSP: ffffbd13003d37b8 RFLAGS: 00000287 RAX: ffff975850b43600 RBX: ffff975850b40200 RCX: 0000000000000000 RDX: 000000003fffffff RSI: 0000000051d383e4 RDI: ffff975850b43618 RBP: ffffbd13003d3800 R8: 0000000000000000 R9: ffff975850b40200 R10: 0000000000000000 R11: 0000000000000000 R12: ffffbd13003d3830 R13: ffff975850b436a8 R14: ffff975850b43600 R15: 0000000000000007 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 9 [ffffbd13003d3808] ip6_pol_route at ffffffff8ddb030c 10 [ffffbd13003d3888] ip6_pol_route_input at ffffffff8ddb068c 11 [ffffbd13003d3898] fib6_rule_lookup at ffffffff8ddf02b5 12 [ffffbd13003d3928] ip6_route_input at ffffffff8ddb0f47 13 [ffffbd13003d3a18] ip6_rcv_finish_core.constprop.0 at ffffffff8dd950d0 14 [ffffbd13003d3a30] ip6_list_rcv_finish.constprop.0 at ffffffff8dd96274 15 [ffffbd13003d3a98] ip6_sublist_rcv at ffffffff8dd96474 16 [ffffbd13003d3af8] ipv6_list_rcv at ffffffff8dd96615 17 [ffffbd13003d3b60] __netif_receive_skb_list_core at ffffffff8dc16fec 18 [ffffbd13003d3be0] netif_receive_skb_list_internal at ffffffff8dc176b3 19 [ffffbd13003d3c50] napi_gro_receive at ffffffff8dc565b9 20 [ffffbd13003d3c80] ice_receive_skb at ffffffffc087e4f5 [ice] 21 [ffffbd13003d3c90] ice_clean_rx_irq at ffffffffc0881b80 [ice] 22 [ffffbd13003d3d20] ice_napi_poll at ffffffffc088232f [ice] 23 [ffffbd13003d3d80] __napi_poll at ffffffff8dc18000 24 [ffffbd13003d3db8] net_rx_action at ffffffff8dc18581 25 [ffffbd13003d3e40] __do_softirq at ffffffff8df352e9 26 [ffffbd13003d3eb0] run_ksoftirqd at ffffffff8ceffe47 27 [ffffbd13003d3ec0] smpboot_thread_fn at ffffffff8cf36a30 28 [ffffbd13003d3ee8] kthread at ffffffff8cf2b39f 29 [ffffbd13003d3f28] ret_from_fork at ffffffff8ce5fa64 30 [ffffbd13003d3f50] ret_from_fork_asm at ffffffff8ce03cbb Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Adrian Oliver <kernel(a)aoliver.ca> Signed-off-by: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi(a)menlosecurity.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: David Ahern <dsahern(a)gmail.com> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Ido Schimmel <idosch(a)idosch.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Simon Horman <horms(a)kernel.org> Cc: Omid Ehtemam-Haghighi <oeh.kernel(a)gmail.com> Cc: netdev(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- v6 -> v7: * Rebased on top of 'net-next' v5 -> v6: * Adjust the comment line lengths in the test script to a maximum of 80 characters * Change memory allocation in inet6_rt_notify from gfp_any() to GFP_ATOMIC for atomic allocation in non-blocking contexts, as suggested by Ido Schimmel * NOTE: I have executed the test script on both bare-metal servers and virtualized environments such as QEMU and vng. In the case of bare-metal, it consistently triggers a soft lockup in under a minute on unpatched kernels. For the virtualized environments, an unpatched kernel compiled with the Ubuntu 24.04 configuration also triggers a soft lockup, though it takes longer; however, it did not trigger a soft lockup on kernels compiled with configurations provided in: https://github.com/linux-netdev/nipa/wiki/How-to-run-netdev-selftests-CI-st… leading to potential false negatives in the test results. I am curious if this test can be executed on a bare-metal machine within a CI system, if such a setup exists, rather than in a virtualized environment. If that’s not possible, how can I apply a different kernel configuration, such as the one used in Ubuntu 24.04, for this test? Please advise. v4 -> v5: * Addressed review comments from Paolo Abeni. * Added additional clarifying comments in the test script. * Minor cleanup performed in the test script. v3 -> v4: * Added RCU primitives to rt6_fill_node(). I found that this function is typically called either with a table lock held or within rcu_read_lock/rcu_read_unlock pairs, except in the following call chain, where the protection is unclear: rt_fill_node() fib6_info_hw_flags_set() mlxsw_sp_fib6_offload_failed_flag_set() mlxsw_sp_router_fib6_event_work() The last function is initialized as a work item in mlxsw_sp_router_fib_event() and scheduled for deferred execution. I am unsure if the execution context of this work item is protected by any table lock or rcu_read_lock/rcu_read_unlock pair, so I have added the protection. Please let me know if this is redundant. * Other review comments addressed v2 -> v3: * Removed redundant rcu_read_lock()/rcu_read_unlock() pairs * Revised the test script based on Ido Schimmel's feedback * Updated the test script to ensure compatibility with the latest iperf3 version * Fixed new warnings generated with 'C=2' in the previous version * Other review comments addressed v1 -> v2: * list_del_rcu() is applied exclusively to legacy multipath code * All occurrences of fib6_siblings have been modified to utilize RCU APIs for annotation and usage. * Additionally, a test script for reproducing the reported issue is included --- net/ipv6/ip6_fib.c | 8 +- net/ipv6/route.c | 45 ++- tools/testing/selftests/net/Makefile | 1 + .../net/ipv6_route_update_soft_lockup.sh | 262 ++++++++++++++++++ 4 files changed, 297 insertions(+), 19 deletions(-) create mode 100755 tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6383263bfd04..c134ba202c4c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1183,8 +1183,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->fib6_siblings, - &sibling->fib6_siblings); + list_add_tail_rcu(&rt->fib6_siblings, + &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, @@ -1245,7 +1245,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } @@ -1963,7 +1963,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d7ce5cf2017a..e23e653de158 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -413,8 +413,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; + struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -440,8 +440,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; - list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, - fib6_siblings) { + list_for_each_entry_rcu(sibling, &match->fib6_siblings, + fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; @@ -5195,14 +5195,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ + rcu_read_lock(); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { - rt = list_first_entry(&rt_last->fib6_siblings, - struct fib6_info, - fib6_siblings); + rt = list_first_or_null_rcu(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); + + rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) @@ -5547,17 +5551,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { - struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; + struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } + + rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } @@ -5721,7 +5729,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); @@ -5733,14 +5741,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, 0) < 0) goto nla_put_failure; - list_for_each_entry_safe(sibling, next_sibling, - &rt->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &rt->fib6_siblings, + fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6, 0) < 0) + AF_INET6, 0) < 0) { + rcu_read_unlock(); + goto nla_put_failure; + } } + rcu_read_unlock(); + nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) @@ -6177,7 +6192,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; @@ -6190,7 +6205,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, - info->nlh, gfp_any()); + info->nlh, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 26a4883a65c9..8c4db5199a42 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -96,6 +96,7 @@ TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py +TEST_PROGS += ipv6_route_update_soft_lockup.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := ncdevmem diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh new file mode 100755 index 000000000000..a6b2b1f9c641 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh @@ -0,0 +1,262 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Testing for potential kernel soft lockup during IPv6 routing table +# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup +# occurs, a kernel panic will be triggered to prevent associated issues. +# +# +# Test Environment Layout +# +# ┌----------------┐ ┌----------------┐ +# | SOURCE_NS | | SINK_NS | +# | NAMESPACE | | NAMESPACE | +# |(iperf3 clients)| |(iperf3 servers)| +# | | | | +# | | | | +# | ┌-----------| nexthops |---------┐ | +# | |veth_source|<--------------------------------------->|veth_sink|<┐ | +# | └-----------|2001:0DB8:1::0:1/96 2001:0DB8:1::1:1/96 |---------┘ | | +# | | ^ 2001:0DB8:1::1:2/96 | | | +# | | . . | fwd | | +# | ┌---------┐ | . . | | | +# | | IPv6 | | . . | V | +# | | routing | | . 2001:0DB8:1::1:80/96| ┌-----┐ | +# | | table | | . | | lo | | +# | | nexthop | | . └--------┴-----┴-┘ +# | | update | | ............................> 2001:0DB8:2::1:1/128 +# | └-------- ┘ | +# └----------------┘ +# +# The test script sets up two network namespaces, source_ns and sink_ns, +# connected via a veth link. Within source_ns, it continuously updates the +# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop +# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a +# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds. +# +# Simultaneously, multiple iperf3 clients within source_ns generate heavy +# outgoing IPv6 traffic. Each client is assigned a unique port number starting +# at 5000 and incrementing sequentially. Each client targets a unique iperf3 +# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface +# using the same port number. +# +# The number of iperf3 servers and clients is set to half of the total +# available cores on each machine. +# +# NOTE: We have tested this script on machines with various CPU specifications, +# ranging from lower to higher performance as listed below. The test script +# effectively triggered a kernel soft lockup on machines running an unpatched +# kernel in under a minute: +# +# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz +# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz +# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz +# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz +# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz +# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz +# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz +# +# On less performant machines, you may need to increase the TEST_DURATION +# parameter to enhance the likelihood of encountering a race condition leading +# to a kernel soft lockup and avoid a false negative result. +# +# NOTE: The test may not produce the expected result in virtualized +# environments (e.g., qemu) due to differences in timing and CPU handling, +# which can affect the conditions needed to trigger a soft lockup. + +source lib.sh +source net_helper.sh + +TEST_DURATION=300 +ROUTING_TABLE_REFRESH_PERIOD=0.01 + +IPERF3_BITRATE="300m" + + +IPV6_NEXTHOP_ADDR_COUNT="128" +IPV6_NEXTHOP_ADDR_MASK="96" +IPV6_NEXTHOP_PREFIX="2001:0DB8:1" + + +SOURCE_TEST_IFACE="veth_source" +SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96" + +SINK_TEST_IFACE="veth_sink" +# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses: +# 2001:0DB8:1::1:1 to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT} +SINK_LOOPBACK_IFACE="lo" +SINK_LOOPBACK_IP_MASK="128" +SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1" + +nexthop_ip_list="" +termination_signal="" +kernel_softlokup_panic_prev_val="" + +terminate_ns_processes_by_pattern() { + local ns=$1 + local pattern=$2 + + for pid in $(ip netns pids ${ns}); do + [ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid + done +} + +cleanup() { + echo "info: cleaning up namespaces and terminating all processes within them..." + + + # Terminate iperf3 instances running in the source_ns. To avoid race + # conditions, first iterate over the PIDs and terminate those + # associated with the bash shells running the + # `while true; do iperf3 -c ...; done` loops. In a second iteration, + # terminate the individual `iperf3 -c ...` instances. + terminate_ns_processes_by_pattern ${source_ns} while + terminate_ns_processes_by_pattern ${source_ns} iperf3 + + # Repeat the same process for sink_ns + terminate_ns_processes_by_pattern ${sink_ns} while + terminate_ns_processes_by_pattern ${sink_ns} iperf3 + + # Check if any iperf3 instances are still running. This could happen + # if a core has entered an infinite loop and the timeout for detecting + # the soft lockup has not expired, but either the test interval has + # already elapsed or the test was terminated manually (e.g., with ^C) + for pid in $(ip netns pids ${source_ns}); do + if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then + echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!" + exit ${ksft_fail} + fi + done + + if [ "$termination_signal" == "SIGINT" ]; then + echo "SKIP: Termination due to ^C (SIGINT)" + elif [ "$termination_signal" == "SIGALRM" ]; then + echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test" + fi + + cleanup_ns ${source_ns} ${sink_ns} + + sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val} +} + +setup_prepare() { + setup_ns source_ns sink_ns + + ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns} + + # Setting up the Source namespace + ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE} + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000 + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up + ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1 + + # Setting up the Sink namespace + ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE} + ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1 + + ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1 + + + # Populate nexthop IPv6 addresses on the test interface in the sink_ns + echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..." + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE}; + done + + # Preparing list of nexthops + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1" + done +} + + +test_soft_lockup_during_routing_table_refresh() { + # Start num_of_iperf_servers iperf3 servers in the sink_ns namespace, + # each listening on ports starting at 5001 and incrementing + # sequentially. Since iperf3 instances may terminate unexpectedly, a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null" + ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + # Wait for the iperf3 servers to be ready + for i in $(seq ${num_of_iperf_servers}); do + port=$(printf '5%03d' ${i}); + wait_local_port_listen ${sink_ns} ${port} tcp + done + + # Continuously refresh the routing table in the background within + # the source_ns namespace + ip netns exec ${source_ns} bash -c " + while \$(ip netns list | grep -q ${source_ns}); do + ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list}; + sleep ${ROUTING_TABLE_REFRESH_PERIOD}; + ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK}; + done &" + + # Start num_of_iperf_servers iperf3 clients in the source_ns namespace, + # each sending TCP traffic on sequential ports starting at 5001. + # Since iperf3 instances may terminate unexpectedly (e.g., if the route + # to the server is deleted in the background during a route refresh), a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null" + ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..." + echo "info: A kernel soft lockup, if detected, results in a kernel panic!" + + wait +} + +# Make sure 'iperf3' is installed, skip the test otherwise +if [ ! -x "$(command -v "iperf3")" ]; then + echo "SKIP: 'iperf3' is not installed. Skipping the test." + exit ${ksft_skip} +fi + +# Determine the number of cores on the machine +num_of_iperf_servers=$(( $(nproc)/2 )) + +# Check if we are running on a multi-core machine, skip the test otherwise +if [ "${num_of_iperf_servers}" -eq 0 ]; then + echo "SKIP: This test is not valid on a single core machine!" + exit ${ksft_skip} +fi + +# Since the kernel soft lockup we're testing causes at least one core to enter +# an infinite loop, destabilizing the host and likely affecting subsequent +# tests, we trigger a kernel panic instead of reporting a failure and +# continuing +kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic) +sysctl -qw kernel.softlockup_panic=1 + +handle_sigint() { + termination_signal="SIGINT" + cleanup + exit ${ksft_skip} +} + +handle_sigalrm() { + termination_signal="SIGALRM" + cleanup + exit ${ksft_pass} +} + +trap handle_sigint SIGINT +trap handle_sigalrm SIGALRM + +(sleep ${TEST_DURATION} && kill -s SIGALRM $$)& + +setup_prepare +test_soft_lockup_during_routing_table_refresh -- 2.43.0

1 year

3
2
0 0

[PATCH net-next 0/8] macsec: inherit lower device's features and TSO limits when offloading

by Sabrina Dubroca

When macsec is offloaded to a NIC, we can take advantage of some of its features, mainly TSO and checksumming. This increases performance significantly. Some features cannot be inherited, because they require additional ops that aren't provided by the macsec netdevice. We also need to inherit TSO limits from the lower device, like VLAN/macvlan devices do. This series also moves the existing macsec offload selftest to the netdevsim selftests before adding tests for the new features. To allow this new selftest to work, netdevsim's hw_features are expanded. Sabrina Dubroca (8): netdevsim: add more hw_features selftests: netdevsim: add a test checking ethtool features macsec: add some of the lower device's features when offloading macsec: clean up local variables in macsec_notify macsec: inherit lower device's TSO limits when offloading selftests: move macsec offload tests from net/rtnetlink to drivers/net/netdvesim selftests: netdevsim: add test toggling macsec offload selftests: netdevsim: add ethtool features to macsec offload tests drivers/net/macsec.c | 64 +++++++--- drivers/net/netdevsim/netdev.c | 6 +- .../selftests/drivers/net/netdevsim/Makefile | 2 + .../selftests/drivers/net/netdevsim/config | 1 + .../drivers/net/netdevsim/ethtool-features.sh | 31 +++++ .../drivers/net/netdevsim/macsec-offload.sh | 117 ++++++++++++++++++ tools/testing/selftests/net/rtnetlink.sh | 68 ---------- 7 files changed, 200 insertions(+), 89 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh create mode 100755 tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh -- 2.47.0

1 year

3
17
0 0

[PATCH net-next v3 6/7] selftests: net: lib: Add kill_process

by Petr Machata

A number of selftests run processes in the background and need to kill them afterwards. Instead for everyone to open-code the kill / wait / redirect mantra, add a helper in net/lib.sh. Convert existing open-code sites. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> CC: Andrew Lunn <andrew+netdev(a)lunn.ch> .../selftests/drivers/net/mlxsw/devlink_trap.sh | 2 +- .../drivers/net/mlxsw/devlink_trap_l3_drops.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_l3_exceptions.sh | 12 ++++++------ .../drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh | 4 ++-- .../net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh | 4 ++-- .../testing/selftests/drivers/net/mlxsw/tc_sample.sh | 4 ++-- .../drivers/net/netdevsim/fib_notifications.sh | 6 +++--- tools/testing/selftests/net/drop_monitor_tests.sh | 2 +- tools/testing/selftests/net/fib_tests.sh | 8 ++++---- .../testing/selftests/net/forwarding/devlink_lib.sh | 2 +- tools/testing/selftests/net/forwarding/lib.sh | 3 +-- tools/testing/selftests/net/forwarding/tc_police.sh | 8 ++++---- tools/testing/selftests/net/lib.sh | 8 ++++++++ 15 files changed, 41 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh index 89b55e946eed..36055279ba92 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh @@ -116,7 +116,7 @@ dev_del_test() log_test "Device delete" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index 160891dcb4bc..db5806d189bb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -595,7 +595,7 @@ irif_disabled_test() log_test "Ingress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip link set dev $rp1 nomaster __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge @@ -645,7 +645,7 @@ erif_disabled_test() log_test "Egress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge devlink_trap_action_set $trap_name "drop" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh index 190c1b6b5365..5d6d88b600f0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh @@ -202,7 +202,7 @@ mtu_value_is_too_small_test() mtu_restore $rp2 - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -235,7 +235,7 @@ __ttl_value_is_too_small_test() log_test "TTL value is too small: TTL=$ttl_val" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -299,7 +299,7 @@ __mc_reverse_path_forwarding_test() log_test "Multicast reverse path forwarding: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower } @@ -347,7 +347,7 @@ __reject_route_test() log_test "Reject route: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip route del unreachable $unreachable tc filter del dev $h1 ingress protocol $proto pref 1 handle 101 flower } @@ -542,7 +542,7 @@ ipv4_lpm_miss_test() log_test "LPM miss: IPv4" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } @@ -569,7 +569,7 @@ ipv6_lpm_miss_test() log_test "LPM miss: IPv6" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index e9a82cae8c9a..4ac1dae92d0f 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh index 878125041fc3..fce885184404 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index 5f6eb965cfd1..7aca8e5922cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -183,7 +183,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -253,7 +253,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh index f6c16cbb6cf7..4599c331240b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh @@ -188,7 +188,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -262,7 +262,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 83a0210e7544..bc7ea2df49fb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -218,7 +218,7 @@ psample_capture_start() psample_capture_stop() { - { kill %% && wait %%; } 2>/dev/null + kill_process %% } __tc_sample_rate_test() @@ -499,7 +499,7 @@ tc_sample_md_out_tc_occ_test() backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]') # Kill mausezahn. - { kill %% && wait %%; } 2>/dev/null + kill_process %% psample_capture_stop diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh index 8d91191a098c..9896580c3d85 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh @@ -94,7 +94,7 @@ route_addition_check() sleep 1 $IP route add $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications $offload_failed rm -f $outfile @@ -148,7 +148,7 @@ route_deletion_check() sleep 1 $IP route del $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile @@ -191,7 +191,7 @@ route_replacement_check() sleep 1 $IP route replace $route dev dummy2 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh index 7c4818c971fc..507d0a82f5f0 100755 --- a/tools/testing/selftests/net/drop_monitor_tests.sh +++ b/tools/testing/selftests/net/drop_monitor_tests.sh @@ -77,7 +77,7 @@ sw_drops_test() rm ${dir}/packets.pcap - { kill %% && wait %%; } 2>/dev/null + kill_process %% timeout 5 dwdump -o sw -w ${dir}/packets.pcap (( $(tshark -r ${dir}/packets.pcap \ -Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) == 0)) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5f3c28fc8624..3ea6f886a210 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -689,7 +689,7 @@ fib6_notify_test() log_test $ret 0 "ipv6 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% #rm errors.txt @@ -736,7 +736,7 @@ fib_notify_test() log_test $ret 0 "ipv4 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm errors.txt @@ -2328,7 +2328,7 @@ ipv4_mangle_test() $IP route del table 123 172.16.101.0/24 dev veth1 $IP rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup @@ -2386,7 +2386,7 @@ ipv6_mangle_test() $IP -6 route del table 123 2001:db8:101::/64 dev veth1 $IP -6 rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 62a05bca1e82..18afa89ebbcc 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -501,7 +501,7 @@ devlink_trap_drop_cleanup() local pref=$1; shift local handle=$1; shift - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8625e3c99f55..7337f398f9cc 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1574,8 +1574,7 @@ stop_traffic() { local pid=${1-%%}; shift - # Suppress noise from killing mausezahn. - { kill $pid && wait $pid; } 2>/dev/null + kill_process "$pid" } declare -A cappid diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 5103f64a71d6..509fdedfcfa1 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -148,7 +148,7 @@ police_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } @@ -198,7 +198,7 @@ police_shared_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% } police_shared_test() @@ -278,7 +278,7 @@ police_mirror_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower @@ -320,7 +320,7 @@ police_pps_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 6bcf5d13879d..24f63e45735d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -434,3 +434,11 @@ xfail_on_veth() "$@" fi } + +kill_process() +{ + local pid=$1; shift + + # Suppress noise from killing the process. + { kill $pid && wait $pid; } 2>/dev/null +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v3 5/7] selftests: net: lib: Move checks from forwarding/lib.sh here

by Petr Machata

For logging to be useful, something has to set RET and retmsg by calling ret_set_ksft_status(). There is a suite of functions to that end in forwarding/lib: check_err, check_fail et.al. Move them to net/lib.sh so that every net test can use them. Existing lib.sh users might be using these same names for their functions. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 73 ------------------- tools/testing/selftests/net/lib.sh | 73 +++++++++++++++++++ 2 files changed, 73 insertions(+), 73 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index d28dbf27c1f0..8625e3c99f55 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -445,79 +445,6 @@ done ############################################################################## # Helpers -# Whether FAILs should be interpreted as XFAILs. Internal. -FAIL_TO_XFAIL= - -check_err() -{ - local err=$1 - local msg=$2 - - if ((err)); then - if [[ $FAIL_TO_XFAIL = yes ]]; then - ret_set_ksft_status $ksft_xfail "$msg" - else - ret_set_ksft_status $ksft_fail "$msg" - fi - fi -} - -check_fail() -{ - local err=$1 - local msg=$2 - - check_err $((!err)) "$msg" -} - -check_err_fail() -{ - local should_fail=$1; shift - local err=$1; shift - local what=$1; shift - - if ((should_fail)); then - check_fail $err "$what succeeded, but should have failed" - else - check_err $err "$what failed" - fi -} - -xfail() -{ - FAIL_TO_XFAIL=yes "$@" -} - -xfail_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW = yes ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - -omit_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW != yes ]]; then - "$@" - fi -} - -xfail_on_veth() -{ - local dev=$1; shift - local kind - - kind=$(ip -j -d link show dev $dev | - jq -r '.[].linkinfo.info_kind') - if [[ $kind = veth ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 4f52b8e48a3a..6bcf5d13879d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -361,3 +361,76 @@ tests_run() $current_test done } + +# Whether FAILs should be interpreted as XFAILs. Internal. +FAIL_TO_XFAIL= + +check_err() +{ + local err=$1 + local msg=$2 + + if ((err)); then + if [[ $FAIL_TO_XFAIL = yes ]]; then + ret_set_ksft_status $ksft_xfail "$msg" + else + ret_set_ksft_status $ksft_fail "$msg" + fi + fi +} + +check_fail() +{ + local err=$1 + local msg=$2 + + check_err $((!err)) "$msg" +} + +check_err_fail() +{ + local should_fail=$1; shift + local err=$1; shift + local what=$1; shift + + if ((should_fail)); then + check_fail $err "$what succeeded, but should have failed" + else + check_err $err "$what failed" + fi +} + +xfail() +{ + FAIL_TO_XFAIL=yes "$@" +} + +xfail_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW = yes ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} + +omit_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW != yes ]]; then + "$@" + fi +} + +xfail_on_veth() +{ + local dev=$1; shift + local kind + + kind=$(ip -j -d link show dev $dev | + jq -r '.[].linkinfo.info_kind') + if [[ $kind = veth ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v3 4/7] selftests: net: lib: Move tests_run from forwarding/lib.sh here

by Petr Machata

It would be good to use the same mechanism for scheduling and dispatching general net tests as the many forwarding tests already use. To that end, move the logging helpers to net/lib.sh so that every net test can use them. Existing lib.sh users might be using the name themselves. However lib.sh is always sourced near the top of the file (checked), and whatever new definition will simply override the one provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 10 ---------- tools/testing/selftests/net/lib.sh | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 41dd14c42c48..d28dbf27c1f0 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1285,16 +1285,6 @@ matchall_sink_create() action drop } -tests_run() -{ - local current_test - - for current_test in ${TESTS:-$ALL_TESTS}; do - in_defer_scope \ - $current_test - done -} - cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 691318b1ec55..4f52b8e48a3a 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -351,3 +351,13 @@ log_info() echo "INFO: $msg" } + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + in_defer_scope \ + $current_test + done +} -- 2.45.0

1 year

1
0
0 0

[PATCH net-next v3 3/7] selftests: net: lib: Move logging from forwarding/lib.sh here

by Petr Machata

Many net selftests invent their own logging helpers. These really should be in a library sourced by these tests. Currently forwarding/lib.sh has a suite of perfectly fine logging helpers, but sourcing a forwarding/ library from a higher-level directory smells of layering violation. In this patch, move the logging helpers to net/lib.sh so that every net test can use them. Together with the logging helpers, it's also necessary to move pause_on_fail(), and EXIT_STATUS and RET. Existing lib.sh users might be using these same names for their functions or variables. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 113 ----------------- tools/testing/selftests/net/lib.sh | 115 ++++++++++++++++++ 2 files changed, 115 insertions(+), 113 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 89c25f72b10c..41dd14c42c48 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -48,7 +48,6 @@ declare -A NETIFS=( : "${WAIT_TIME:=5}" # Whether to pause on, respectively, after a failure and before cleanup. -: "${PAUSE_ON_FAIL:=no}" : "${PAUSE_ON_CLEANUP:=no}" # Whether to create virtual interfaces, and what netdevice type they should be. @@ -446,22 +445,6 @@ done ############################################################################## # Helpers -# Exit status to return at the end. Set in case one of the tests fails. -EXIT_STATUS=0 -# Per-test return value. Clear at the beginning of each test. -RET=0 - -ret_set_ksft_status() -{ - local ksft_status=$1; shift - local msg=$1; shift - - RET=$(ksft_status_merge $RET $ksft_status) - if (( $? )); then - retmsg=$msg - fi -} - # Whether FAILs should be interpreted as XFAILs. Internal. FAIL_TO_XFAIL= @@ -535,102 +518,6 @@ xfail_on_veth() fi } -log_test_result() -{ - local test_name=$1; shift - local opt_str=$1; shift - local result=$1; shift - local retmsg=$1; shift - - printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" - if [[ $retmsg ]]; then - printf "\t%s\n" "$retmsg" - fi -} - -pause_on_fail() -{ - if [[ $PAUSE_ON_FAIL == yes ]]; then - echo "Hit enter to continue, 'q' to quit" - read a - [[ $a == q ]] && exit 1 - fi -} - -handle_test_result_pass() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" " OK " -} - -handle_test_result_fail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" FAIL "$retmsg" - pause_on_fail -} - -handle_test_result_xfail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" - pause_on_fail -} - -handle_test_result_skip() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" SKIP "$retmsg" -} - -log_test() -{ - local test_name=$1 - local opt_str=$2 - - if [[ $# -eq 2 ]]; then - opt_str="($opt_str)" - fi - - if ((RET == ksft_pass)); then - handle_test_result_pass "$test_name" "$opt_str" - elif ((RET == ksft_xfail)); then - handle_test_result_xfail "$test_name" "$opt_str" - elif ((RET == ksft_skip)); then - handle_test_result_skip "$test_name" "$opt_str" - else - handle_test_result_fail "$test_name" "$opt_str" - fi - - EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) - return $RET -} - -log_test_skip() -{ - RET=$ksft_skip retmsg= log_test "$@" -} - -log_test_xfail() -{ - RET=$ksft_xfail retmsg= log_test "$@" -} - -log_info() -{ - local msg=$1 - - echo "INFO: $msg" -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index c8991cc6bf28..691318b1ec55 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -9,6 +9,9 @@ source "$net_dir/lib/sh/defer.sh" : "${WAIT_TIMEOUT:=20}" +# Whether to pause on after a failure. +: "${PAUSE_ON_FAIL:=no}" + BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms # Kselftest framework constants. @@ -20,6 +23,11 @@ ksft_skip=4 # namespace list created by setup_ns NS_LIST=() +# Exit status to return at the end. Set in case one of the tests fails. +EXIT_STATUS=0 +# Per-test return value. Clear at the beginning of each test. +RET=0 + ############################################################################## # Helpers @@ -236,3 +244,110 @@ tc_rule_handle_stats_get() | jq ".[] | select(.options.handle == $handle) | \ .options.actions[0].stats$selector" } + +ret_set_ksft_status() +{ + local ksft_status=$1; shift + local msg=$1; shift + + RET=$(ksft_status_merge $RET $ksft_status) + if (( $? )); then + retmsg=$msg + fi +} + +log_test_result() +{ + local test_name=$1; shift + local opt_str=$1; shift + local result=$1; shift + local retmsg=$1; shift + + printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" + if [[ $retmsg ]]; then + printf "\t%s\n" "$retmsg" + fi +} + +pause_on_fail() +{ + if [[ $PAUSE_ON_FAIL == yes ]]; then + echo "Hit enter to continue, 'q' to quit" + read a + [[ $a == q ]] && exit 1 + fi +} + +handle_test_result_pass() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" " OK " +} + +handle_test_result_fail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" FAIL "$retmsg" + pause_on_fail +} + +handle_test_result_xfail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" + pause_on_fail +} + +handle_test_result_skip() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" SKIP "$retmsg" +} + +log_test() +{ + local test_name=$1 + local opt_str=$2 + + if [[ $# -eq 2 ]]; then + opt_str="($opt_str)" + fi + + if ((RET == ksft_pass)); then + handle_test_result_pass "$test_name" "$opt_str" + elif ((RET == ksft_xfail)); then + handle_test_result_xfail "$test_name" "$opt_str" + elif ((RET == ksft_skip)); then + handle_test_result_skip "$test_name" "$opt_str" + else + handle_test_result_fail "$test_name" "$opt_str" + fi + + EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) + return $RET +} + +log_test_skip() +{ + RET=$ksft_skip retmsg= log_test "$@" +} + +log_test_xfail() +{ + RET=$ksft_xfail retmsg= log_test "$@" +} + +log_info() +{ + local msg=$1 + + echo "INFO: $msg" +} -- 2.45.0

1 year

1
0
0 0

[PATCH v7 0/5] selftests: kvm: s390: Add ucontrol memory selftests

by Christoph Schlameuss

This patch series adds a some not yet picked selftests to the kvm s390x selftest suite. The additional test cases are covering: * Assert KVM_EXIT_S390_UCONTROL exit on not mapped memory access * Assert functionality of storage keys in ucontrol VM * Assert that memory region operations are rejected for ucontrol VMs Running the test cases requires sys_admin capabilities to start the ucontrol VM. This can be achieved by running as root or with a command like: sudo setpriv --reuid nobody --inh-caps -all,+sys_admin \ --ambient-caps -all,+sys_admin --bounding-set -all,+sys_admin \ ./ucontrol_test --- The patches in this series have been part of the previous patch series. The test cases added here do depend on the fixture added in the earlier patches. From v5 PATCH 7-9 the segment and page table generation has been removed and DAT has been disabled. Since DAT is not necessary to validate the KVM code. https://lore.kernel.org/kvm/20240807154512.316936-1-schlameuss@linux.ibm.co… v7: - skip uc_skey test when execution is in vsie v6: - add instruction intercept handling for skey specific instructions (iske, sske, rrbe) in addition to kss intercept to work properly on all machines - reorder local variables - fixup some method comments - add a patch correcting the IP.b value length a debug message v5: - rebased to current upstream master - corrected assertion on 0x00 to 0 - reworded fixup commit so that it can be merged on top of current upstream v4: - fix whitespaces in pointer function arguments (thanks Claudio) - fix whitespaces in comments (thanks Janosch) v3: - fix skey assertion (thanks Claudio) - introduce a wrapper around UCAS map and unmap ioctls to improve readability (Claudio) - add an displacement to accessed memory to assert translation intercepts actually point to segments to the uc_map_unmap test - add an misaligned failing mapping try to the uc_map_unmap test v2: - Reenable KSS intercept and handle it within skey test. - Modify the checked register between storing (sske) and reading (iske) it within the test program to make sure the. - Add an additional state assertion in the end of uc_skey - Fix some typos and white spaces. v1: - Remove segment and page table generation and disable DAT. This is not necessary to validate the KVM code. Christoph Schlameuss (5): selftests: kvm: s390: Add uc_map_unmap VM test case selftests: kvm: s390: Add uc_skey VM test case selftests: kvm: s390: Verify reject memory region operations for ucontrol VMs selftests: kvm: s390: Fix whitespace confusion in ucontrol test selftests: kvm: s390: correct IP.b length in uc_handle_sieic debug output .../selftests/kvm/include/s390x/processor.h | 6 + .../selftests/kvm/s390x/ucontrol_test.c | 321 +++++++++++++++++- 2 files changed, 319 insertions(+), 8 deletions(-) -- 2.47.0

1 year

2
7
0 0

[PATCH] kunit: string-stream: Fix a UAF bug in kunit_init_suite()

by Jinjie Ruan

In kunit_debugfs_create_suite(), if alloc_string_stream() fails in the kunit_suite_for_each_test_case() loop, the "suite->log = stream" has assigned before, and the error path only free the suite->log's stream memory but not set it to NULL in string_stream_destroy(), so the later string_stream_clear() of suite->log in kunit_init_suite() will cause below UAF bug. Set stream pointer to NULL after free in string_stream_destroy() to fix it. Unable to handle kernel paging request at virtual address 006440150000030d Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [006440150000030d] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: iio_test_gts industrialio_gts_helper cfg80211 rfkill ipv6 [last unloaded: iio_test_gts] CPU: 5 UID: 0 PID: 6253 Comm: modprobe Tainted: G B W N 6.12.0-rc4+ #458 Tainted: [B]=BAD_PAGE, [W]=WARN, [N]=TEST Hardware name: linux,dummy-virt (DT) pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : string_stream_clear+0x54/0x1ac lr : string_stream_clear+0x1a8/0x1ac sp : ffffffc080b47410 x29: ffffffc080b47410 x28: 006440550000030d x27: ffffff80c96b5e98 x26: ffffff80c96b5e80 x25: ffffffe461b3f6c0 x24: 0000000000000003 x23: ffffff80c96b5e88 x22: 1ffffff019cdf4fc x21: dfffffc000000000 x20: ffffff80ce6fa7e0 x19: 032202a80000186d x18: 0000000000001840 x17: 0000000000000000 x16: 0000000000000000 x15: ffffffe45c355cb4 x14: ffffffe45c35589c x13: ffffffe45c03da78 x12: ffffffb810168e75 x11: 1ffffff810168e74 x10: ffffffb810168e74 x9 : dfffffc000000000 x8 : 0000000000000004 x7 : 0000000000000003 x6 : 0000000000000001 x5 : ffffffc080b473a0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000001 x1 : ffffffe462fbf620 x0 : dfffffc000000000 Call trace: string_stream_clear+0x54/0x1ac __kunit_test_suites_init+0x108/0x1d8 kunit_exec_run_tests+0xb8/0x100 kunit_module_notify+0x400/0x55c notifier_call_chain+0xfc/0x3b4 blocking_notifier_call_chain+0x68/0x9c do_init_module+0x24c/0x5c8 load_module+0x4acc/0x4e90 init_module_from_file+0xd4/0x128 idempotent_init_module+0x2d4/0x57c __arm64_sys_finit_module+0xac/0x100 invoke_syscall+0x6c/0x258 el0_svc_common.constprop.0+0x160/0x22c do_el0_svc+0x44/0x5c el0_svc+0x48/0xb8 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 Code: f9400753 d2dff800 f2fbffe0 d343fe7c (38e06b80) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception Cc: stable(a)vger.kernel.org Fixes: a3fdf784780c ("kunit: string-stream: Decouple string_stream from kunit") Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- lib/kunit/string-stream.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c index 54f4fdcbfac8..00ad518b730b 100644 --- a/lib/kunit/string-stream.c +++ b/lib/kunit/string-stream.c @@ -178,6 +178,7 @@ void string_stream_destroy(struct string_stream *stream) string_stream_clear(stream); kfree(stream); + stream = NULL; } static void resource_free_string_stream(void *p) -- 2.34.1

1 year

3
6
0 0

[PATCH] selftests: hugetlb_dio: Check for initial conditions to skip in the start

by Muhammad Usama Anjum

The test should be skipped if initial conditions aren't fulfilled in the start instead of failing and outputting non-compliant TAP logs. This kind of failure pollutes the results. The initial conditions are: - The test should only execute if /tmp file can be allocated. - The test should only execute if huge pages are free. Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> --- Before: TAP version 13 1..4 Bail out! Error opening file : Read-only file system (30) # Planned tests != run tests (4 != 0) # Totals: pass:0 fail:0 xfail:0 xpass:0 skip:0 error:0 After: TAP version 13 1..0 # SKIP Unable to allocate file: Read-only file system --- tools/testing/selftests/mm/hugetlb_dio.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index f9ac20c657ec6..60001c142ce99 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -44,13 +44,6 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) if (fd < 0) ksft_exit_fail_perror("Error opening file\n"); - /* Get the free huge pages before allocation */ - free_hpage_b = get_free_hugepages(); - if (free_hpage_b == 0) { - close(fd); - ksft_exit_skip("No free hugepage, exiting!\n"); - } - /* Allocate a hugetlb page */ orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0); if (orig_buffer == MAP_FAILED) { @@ -94,8 +87,20 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) int main(void) { size_t pagesize = 0; + int fd; ksft_print_header(); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno)); + close(fd); + + /* Check if huge pages are free */ + if (!get_free_hugepages()) + ksft_exit_skip("No free hugepage, exiting\n"); + ksft_set_plan(4); /* Get base page size */ -- 2.39.5

1 year

4
10
0 0

[PATCH v2 0/3] kunit: Add support for LoongArch

by Thomas Weißschuh

Enable LoongArch support in kunit. Example: $ ./tools/testing/kunit/kunit.py run --arch=loongarch --cross_compile=$CROSS_COMPILE [13:32:45] Configuring KUnit Kernel ... [13:32:45] Building KUnit Kernel ... Populating config with: $ make ARCH=loongarch olddefconfig CROSS_COMPILE=$CROSS_COMPILE Building with: $ make all compile_commands.json ARCH=loongarch --jobs=8 CROSS_COMPILE=$CROSS_COMPILE [13:32:48] Starting KUnit Kernel (1/1)... [13:32:48] ============================================================ Running tests with: $ qemu-system-loongarch64 -nodefaults -m 1024 -kernel .kunit/arch/loongarch/boot/vmlinux.elf -append 'kunit.enable=1 console=ttyS0 kunit_shutdown=poweroff' -no-reboot -nographic -serial stdio -machine virt -device pvpanic-pci -cpu max ... [13:33:14] ============================================================ [13:33:14] Testing complete. Ran 493 tests: passed: 453, skipped: 40 [13:33:14] Elapsed time: 28.862s total, 0.002s configuring, 2.526s building, 26.302s running This series is meant to be merged through the kselftest tree. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Changes in v2: - Drop already applied patch - Pick up review tags - Add SPDX header - Link to v1: https://lore.kernel.org/r/20241014-kunit-loongarch-v1-0-1699b2ad6099@linutr… --- Thomas Weißschuh (3): kunit: qemu_configs: Add LoongArch config kunit: tool: Allow overriding the shutdown mode from qemu config kunit: qemu_configs: loongarch: Enable shutdown tools/testing/kunit/kunit_kernel.py | 4 +++- tools/testing/kunit/qemu_configs/loongarch.py | 21 +++++++++++++++++++++ 2 files changed, 24 insertions(+), 1 deletion(-) --- base-commit: 2d5404caa8c7bb5c4e0435f94b28834ae5456623 change-id: 20241014-kunit-loongarch-98a5b756e818 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

1 year

1
3
0 0

[PATCH v3] lib/math: Add int_sqrt test suite

by Luis Felipe Hernandez

Adds test suite for integer based square root function. The test suite is designed to verify the correctness of the int_sqrt() math library function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- Changes in v2 - Add new line at the end of int_sqrt_kunit.c - Add explicit header includes for MODULE_* macros, strscpy, and ULONG_MAX Changes in v3 - Remove unnecesary new line after Kconfig entry for INT_SQRT_KUNIT_TEST - Correct int_sqrt instances with int_sqrt() in commit message and kconfig entry desc - Fix limits.h header include path --- lib/Kconfig.debug | 15 ++++++++++ lib/math/Makefile | 1 + lib/math/tests/Makefile | 1 + lib/math/tests/int_sqrt_kunit.c | 51 +++++++++++++++++++++++++++++++++ 4 files changed, 68 insertions(+) create mode 100644 lib/math/tests/int_sqrt_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7312ae7c3cc5..c83f5dc9bb48 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2993,6 +2993,21 @@ config TEST_OBJPOOL If unsure, say N. +config INT_SQRT_KUNIT_TEST + tristate "Integer square root test test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_sqrt() function, + which performs square root calculation. The test suite checks + various scenarios, including edge cases, to ensure correctness. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the square root + function. + + If unsure, say N + endif # RUNTIME_TESTING_MENU config ARCH_USE_MEMTEST diff --git a/lib/math/Makefile b/lib/math/Makefile index 3ef11305f8d2..25bcb968b369 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -9,3 +9,4 @@ obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_TEST_MULDIV64) += test_mul_u64_u64_div_u64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o +obj-y += tests/ diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile index 6a169123320a..e1a79f093b2d 100644 --- a/lib/math/tests/Makefile +++ b/lib/math/tests/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o +obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += int_sqrt_kunit.o diff --git a/lib/math/tests/int_sqrt_kunit.c b/lib/math/tests/int_sqrt_kunit.c new file mode 100644 index 000000000000..3590142d2012 --- /dev/null +++ b/lib/math/tests/int_sqrt_kunit.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <kunit/test.h> +#include <linux/limits.h> +#include <linux/math.h> +#include <linux/module.h> +#include <linux/string.h> + +struct test_case_params { + unsigned long x; + unsigned long expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 0, 0, "edge-case: square root of 0" }, + { 4, 2, "perfect square: square root of 4" }, + { 81, 9, "perfect square: square root of 9" }, + { 2, 1, "non-perfect square: square root of 2" }, + { 5, 2, "non-perfect square: square root of 5"}, + { ULONG_MAX, 4294967295, "large input"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_sqrt, params, get_desc); + +static void int_sqrt_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_sqrt(tc->x)); +} + +static struct kunit_case math_int_sqrt_test_cases[] = { + KUNIT_CASE_PARAM(int_sqrt_test, int_sqrt_gen_params), + {} +}; + +static struct kunit_suite int_sqrt_test_suite = { + .name = "math-int_sqrt", + .test_cases = math_int_sqrt_test_cases, +}; + +kunit_test_suites(&int_sqrt_test_suite); + +MODULE_DESCRIPTION("math.int_sqrt KUnit test suite"); +MODULE_LICENSE("GPL"); -- 2.47.0

1 year

3
7
0 0

[PATCH net] selftests: wireguard: load nf_conntrack if it's not present

by Hangbin Liu

Some distros may not load nf_conntrack by default, which will cause subsequent nf_conntrack settings to fail. Let's load this module if it's not loaded by default. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- tools/testing/selftests/wireguard/netns.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..508b391e8d9a 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -66,6 +66,7 @@ cleanup() { orig_message_cost="$(< /proc/sys/net/core/message_cost)" trap cleanup EXIT printf 0 > /proc/sys/net/core/message_cost +lsmod | grep -q nf_conntrack || modprobe nf_conntrack ip netns del $netns0 2>/dev/null || true ip netns del $netns1 2>/dev/null || true -- 2.46.0

1 year

2
1
0 0

[PATCH bpf v3 0/2] bpf: fix recursive lock and add test

by Jiayuan Chen

1. fix recursive lock when ebpf prog return SK_PASS. 2. add selftest to reproduce recursive lock. Note that if just the selftest merged without first patch, the test case will definitely fail, because the issue of deadlock is inevitable. --- v2->v3: fix line length reported by patchwork. (max_line_length is set to 80 in patchwork but default is 100 in kernel tree) v1->v2: 1.inspired by martin.lau to add selftest to reproduce the issue. 2. follow the community rules for patch. v1: https://lore.kernel.org/bpf/55fc6114-7e64-4b65-86d2-92cfd1e9e92f@linux.dev/… --- Jiayuan Chen (2): bpf: fix recursive lock when verdict program return SK_PASS selftests/bpf: Add some tests with sockmap SK_PASS net/core/skmsg.c | 4 +- .../selftests/bpf/prog_tests/sockmap_basic.c | 54 +++++++++++++++++++ .../bpf/progs/test_sockmap_pass_prog.c | 2 +- 3 files changed, 57 insertions(+), 3 deletions(-) -- 2.43.5

1 year

1
2
0 0

[PATCH v4 0/3] rust: kunit: Support KUnit tests with a user-space like syntax

by David Gow

This series was originally written by José Expósito, and has been modified and updated by Matt Gilbride and myself. The original version can be found here: https://github.com/Rust-for-Linux/linux/pull/950 Add support for writing KUnit tests in Rust. While Rust doctests are already converted to KUnit tests and run, they're really better suited for examples, rather than as first-class unit tests. This series implements a series of direct Rust bindings for KUnit tests, as well as a new macro which allows KUnit tests to be written using a close variant of normal Rust unit test syntax. The only change required is replacing '#[cfg(test)]' with '#[kunit_tests(kunit_test_suite_name)]' An example test would look like: #[kunit_tests(rust_kernel_hid_driver)] mod tests { use super::*; use crate::{c_str, driver, hid, prelude::*}; use core::ptr; struct SimpleTestDriver; impl Driver for SimpleTestDriver { type Data = (); } #[test] fn rust_test_hid_driver_adapter() { let mut hid = bindings::hid_driver::default(); let name = c_str!("SimpleTestDriver"); static MODULE: ThisModule = unsafe { ThisModule::from_ptr(ptr::null_mut()) }; let res = unsafe { <hid::Adapter<SimpleTestDriver> as driver::DriverOps>::register(&mut hid, name, &MODULE) }; assert_eq!(res, Err(ENODEV)); // The mock returns -19 } } Please give this a go, and make sure I haven't broken it! There's almost certainly a lot of improvements which can be made -- and there's a fair case to be made for replacing some of this with generated C code which can use the C macros -- but this is hopefully an adequate implementation for now, and the interface can (with luck) remain the same even if the implementation changes. A few small notable missing features: - Attributes (like the speed of a test) are hardcoded to the default value. - Similarly, the module name attribute is hardcoded to NULL. In C, we use the KBUILD_MODNAME macro, but I couldn't find a way to use this from Rust which wasn't more ugly than just disabling it. - Assertions are not automatically rewritten to use KUnit assertions. --- Changes since v3: https://lore.kernel.org/linux-kselftest/20241030045719.3085147-2-davidgow@g… - The kunit_unsafe_test_suite!() macro now panic!s if the suite name is too long, triggering a compile error. (Thanks, Alice!) - The #[kunit_tests()] macro now preserves span information, so errors can be better reported. (Thanks, Boqun!) - The example tests have been updated to no longer use assert_eq!() with a constant bool argument (which triggered a clippy warning now we have the span info). Changes since v2: https://lore.kernel.org/linux-kselftest/20241029092422.2884505-1-davidgow@g… - Include missing rust/macros/kunit.rs file from v2. (Thanks Boqun!) - The kunit_unsafe_test_suite!() macro will truncate the name of the suite if it is too long. (Thanks Alice!) - The proc macro now emits an error if the suite name is too long. - We no longer needlessly use UnsafeCell<> in kunit_unsafe_test_suite!(). (Thanks Alice!) Changes since v1: https://lore.kernel.org/lkml/20230720-rustbind-v1-0-c80db349e3b5@google.com… - Rebase on top of the latest rust-next (commit 718c4069896c) - Make kunit_case a const fn, rather than a macro (Thanks Boqun) - As a result, the null terminator is now created with kernel::kunit::kunit_case_null() - Use the C kunit_get_current_test() function to implement in_kunit_test(), rather than re-implementing it (less efficiently) ourselves. Changes since the GitHub PR: - Rebased on top of kselftest/kunit - Add const_mut_refs feature This may conflict with https://lore.kernel.org/lkml/20230503090708.2524310-6-nmi@metaspace.dk/ - Add rust/macros/kunit.rs to the KUnit MAINTAINERS entry --- José Expósito (3): rust: kunit: add KUnit case and suite macros rust: macros: add macro to easily run KUnit tests rust: kunit: allow to know if we are in a test MAINTAINERS | 1 + rust/kernel/kunit.rs | 194 +++++++++++++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + rust/macros/kunit.rs | 168 +++++++++++++++++++++++++++++++++++++ rust/macros/lib.rs | 29 +++++++ 5 files changed, 393 insertions(+) create mode 100644 rust/macros/kunit.rs -- 2.47.0.199.ga7371fff76-goog

1 year

3
11
0 0

[PROBLEM] selftests/bpf/progs/test_tunnel_kern.c: 678: 41-47: ERROR: application of sizeof to pointer

by Mirsad Todorovac

Hi, all! In the linux-next tree, next-20241108, coccinelle found an error. In the line 617, ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt)); In the line 678, ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); when 592 struct local_geneve_opt local_gopt; 593 struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; and 652 struct local_geneve_opt local_gopt; 653 struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; So, in all other call to bpf_skb_set_tunnel_opt(), the third parameter is the size of the struct, not the size of the pointer: ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:193: ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:273: ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:349: ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:388: ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:617: ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt)); ./tools/testing/selftests/bpf/progs/test_tunnel_kern.c:678: ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); =========================================== 587 SEC("tc") 588 int geneve_set_tunnel(struct __sk_buff *skb) 589 { 590 int ret; 591 struct bpf_tunnel_key key; 592 struct local_geneve_opt local_gopt; 593 struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; 594 595 __builtin_memset(&key, 0x0, sizeof(key)); 596 key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ 597 key.tunnel_id = 2; 598 key.tunnel_tos = 0; 599 key.tunnel_ttl = 64; 600 601 __builtin_memset(gopt, 0x0, sizeof(local_gopt)); 602 gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ 603 gopt->type = 0x08; 604 gopt->r1 = 0; 605 gopt->r2 = 0; 606 gopt->r3 = 0; 607 gopt->length = 2; /* 4-byte multiple */ 608 *(int *) &gopt->opt_data = bpf_htonl(0xdeadbeef); 609 610 ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 611 BPF_F_ZERO_CSUM_TX); 612 if (ret < 0) { 613 log_err(ret); 614 return TC_ACT_SHOT; 615 } 616 617 → ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt)); 618 if (ret < 0) { 619 log_err(ret); 620 return TC_ACT_SHOT; 621 } 622 623 return TC_ACT_OK; 624 } 648 SEC("tc") 649 int ip6geneve_set_tunnel(struct __sk_buff *skb) 650 { 651 struct bpf_tunnel_key key; 652 struct local_geneve_opt local_gopt; 653 struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; 654 int ret; 655 656 __builtin_memset(&key, 0x0, sizeof(key)); 657 key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ 658 key.tunnel_id = 22; 659 key.tunnel_tos = 0; 660 key.tunnel_ttl = 64; 661 662 ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 663 BPF_F_TUNINFO_IPV6); 664 if (ret < 0) { 665 log_err(ret); 666 return TC_ACT_SHOT; 667 } 668 669 __builtin_memset(gopt, 0x0, sizeof(local_gopt)); 670 gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ 671 gopt->type = 0x08; 672 gopt->r1 = 0; 673 gopt->r2 = 0; 674 gopt->r3 = 0; 675 gopt->length = 2; /* 4-byte multiple */ 676 *(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef); 677 678 → ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); 679 if (ret < 0) { 680 log_err(ret); 681 return TC_ACT_SHOT; 682 } 683 684 return TC_ACT_OK; 685 } SOLUTION: Fixes: 5ddafcc377f98 ("selftests/bpf: Fix a few tests for GCC related warnings.") ------------------ diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 32127f1cd687..b53d367451b2 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -675,7 +675,7 @@ int ip6geneve_set_tunnel(struct __sk_buff *skb) gopt->length = 2; /* 4-byte multiple */ *(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef); - ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); + ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt)); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; -- Best regards, MT

1 year

1
0
0 0

[PATCH] kunit: skb: use "gfp" variable instead of hardcoding GFP_KERNEL

by Dan Carpenter

The intent here was clearly to use the gfp variable flags instead of hardcoding GFP_KERNEL. All the callers pass GFP_KERNEL as the gfp flags so this doesn't affect runtime. Fixes: b3231d353a51 ("kunit: add a convenience allocation wrapper for SKBs") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> --- include/kunit/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/kunit/skbuff.h b/include/kunit/skbuff.h index 44d12370939a..345e1e8f0312 100644 --- a/include/kunit/skbuff.h +++ b/include/kunit/skbuff.h @@ -29,7 +29,7 @@ static void kunit_action_kfree_skb(void *p) static inline struct sk_buff *kunit_zalloc_skb(struct kunit *test, int len, gfp_t gfp) { - struct sk_buff *res = alloc_skb(len, GFP_KERNEL); + struct sk_buff *res = alloc_skb(len, gfp); if (!res || skb_pad(res, len)) return NULL; -- 2.45.2

1 year

3
2
0 0

[PATCH net-next v8 0/6] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v8, see changelog below. This revision is a quick follow-up to v7 and only drops the unneeded exports in patch 2. No other changes. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Important call out in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspend0: - set defer_hard_irqs to 0 - set gro_flush_timeout to 0 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over nearly 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results shift between submissions, but the relative differences are equivalent. As patches are rebased, several factors likely influence overall performance. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. - suspend0, which sets defer_hard_irqs and gro_flush_timeout to 0, has nearly the same performance as the base case (this is FAQ item #1). The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 199946 112 239 416 26 12973 11343 defer10 200K 199971 54 124 142 29 19412 17460 defer20 200K 199986 60 130 153 26 15644 14095 defer50 200K 200025 79 144 182 23 12122 11632 defer200 200K 199999 164 254 309 19 8923 9635 fullbusy 200K 199998 46 118 133 100 43658 23133 napibusy 200K 199983 100 237 277 56 24840 24716 suspend0 200K 200020 105 249 432 30 14264 11796 suspend10 200K 199950 53 123 141 32 19518 16903 suspend20 200K 200037 58 126 151 30 16426 14736 suspend50 200K 199961 73 136 177 26 13310 12633 suspend200 200K 199998 149 251 306 21 9566 10203 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400014 139 269 707 41 9476 9343 defer10 400K 400016 59 133 166 53 13991 12989 defer20 400K 399952 67 140 172 47 12063 11644 defer50 400K 400007 87 162 198 39 9384 9880 defer200 400K 399979 181 274 330 31 7089 8430 fullbusy 400K 399987 50 123 156 100 21827 16037 napibusy 400K 400014 76 222 272 83 18185 16529 suspend0 400K 400015 127 350 776 47 10699 9603 suspend10 400K 400023 57 129 164 54 13758 13178 suspend20 400K 400043 62 135 169 49 12071 11826 suspend50 400K 400071 76 149 186 42 10011 10301 suspend200 400K 399961 154 269 327 34 7827 8774 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 599951 149 266 574 61 9265 8876 defer10 600K 600006 71 147 203 76 11866 10936 defer20 600K 600123 76 152 203 66 10430 10342 defer50 600K 600162 95 172 217 54 8526 9142 defer200 600K 599942 200 301 357 46 6977 8212 fullbusy 600K 599990 55 127 177 100 14551 13983 napibusy 600K 600035 63 160 250 96 13937 14140 suspend0 600K 599903 127 320 732 68 10166 8963 suspend10 600K 599908 63 137 192 69 10902 11100 suspend20 600K 599961 66 141 194 65 9976 10370 suspend50 600K 599973 80 159 204 57 8678 9381 suspend200 600K 600010 157 277 346 48 7133 8381 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800039 181 300 536 87 9585 8304 defer10 800K 800038 181 530 939 96 10564 8970 defer20 800K 800029 112 225 329 90 10056 8935 defer50 800K 799999 120 208 296 82 9234 8562 defer200 800K 800066 227 338 401 63 7117 8129 fullbusy 800K 800040 61 134 190 100 10913 12608 napibusy 800K 799944 64 141 214 99 10828 12588 suspend0 800K 799911 126 248 509 85 9346 8498 suspend10 800K 800006 69 143 200 83 9410 9845 suspend20 800K 800120 74 150 207 78 8786 9454 suspend50 800K 799989 87 168 224 71 7946 8833 suspend200 800K 799987 160 292 357 62 6923 8229 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 906879 4079 5751 6216 98 9496 7904 defer10 1000K 860849 3643 6274 6730 99 10040 8676 defer20 1000K 896063 3298 5840 6349 98 9620 8237 defer50 1000K 919782 2962 5513 5807 97 9284 7951 defer200 1000K 970941 3059 5348 5984 95 8593 7959 fullbusy 1000K 999950 70 150 207 100 8732 10777 napibusy 1000K 999996 78 154 223 100 8722 10656 suspend0 1000K 949706 2666 5770 6660 99 9071 8046 suspend10 1000K 1000024 80 160 220 92 8137 9035 suspend20 1000K 1000059 83 165 226 89 7850 8804 suspend50 1000K 999955 95 180 240 84 7411 8459 suspend200 1000K 999914 163 299 366 77 6833 8078 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1037654 4184 5453 5810 100 8411 7938 defer10 MAX 905607 4840 6151 6380 100 9639 8431 defer20 MAX 986463 4455 5594 5796 100 8848 8110 defer50 MAX 1077030 4000 5073 5299 100 8104 7920 defer200 MAX 1040728 4152 5385 5765 100 8379 7849 fullbusy MAX 1247536 3518 3935 3984 100 6998 7930 napibusy MAX 1136310 3799 7756 9964 100 7670 7877 suspend0 MAX 1057509 4132 5724 6185 100 8253 7918 suspend10 MAX 1215147 3580 3957 4041 100 7185 7944 suspend20 MAX 1216469 3576 3953 3988 100 7175 7950 suspend50 MAX 1215871 3577 3961 4075 100 7181 7949 suspend200 MAX 1216882 3556 3951 3988 100 7175 7955 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2 can take control from Loop 1, if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2 and 3 "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2, which essentially tilts this in favour of Loop 3. If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3 cannot take control from Loop 1. Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. This is shown in the results above: compare suspend0 with the base case. Note that the lack of napi_defer_hard_irqs and gro_flush_timeout produce similar results for both, which encourages the use of napi_defer_hard_irqs and gro_flush_timeout in addition to irq_suspend_timeout. - Can the new timeout value be threaded through the new epoll ioctl ? It is possible, but presents challenges for userspace. User applications must ensure that the file descriptors added to epoll contexts have the same NAPI ID to support busy polling. An epoll context is not permanently tied to any particular NAPI ID. So, a user application could decide to clear the file descriptors from the context and add a new set of file descriptors with a different NAPI ID to the context. Busy polling would work as expected, but the meaning of the suspend timeout becomes ambiguous because IRQs are not inherently associated with epoll contexts, but rather with the NAPI. The user program would need to reissue the ioctl to set the irq_suspend_timeout, but the napi_defer_hard_irqs and gro_flush_timeout settings would come from the NAPI's napi_config (which are set either by sysfs or by netlink). Such an interface seems awkard to use from a user perspective. Further, IRQs are related to NAPIs, which is why they are stored in the napi_config space. Putting the irq_suspend_timeout in the epoll context while other IRQ deferral mechanisms remain in the NAPI's napi_config space seems like an odd design choice. We've opted to keep all of the IRQ deferral parameters together and place the irq_suspend_timeout in napi_config. This has nice benefits for userspace: if a user app were to remove all file descriptors from an epoll context and add new file descriptors with a new NAPI ID, the correct suspend timeout for that NAPI ID would be used automatically without the user application needing to do anything (like re-issuing an ioctl, for example). All IRQ deferral related parameters are in one place and can all be set the same way: with netlink. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the results. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v8: - Update patch 2 to drop the exports, as requested by Jakub. v7: https://lore.kernel.org/netdev/20241108023912.98416-1-jdamato@fastly.com/ - Jakub noted that patch 2 adds unnecessary complexity by checking the suspend timeout in the NAPI loop. This makes the code more complicated and difficult to reason about. He's right; we've dropped patch 2 which simplifies this series. - Updated the cover letter with a full re-run of all test cases. - Updated FAQ #2. v6: https://lore.kernel.org/netdev/20241104215542.215919-1-jdamato@fastly.com/ - Updated the cover letter with a full re-run of all test cases, including a new case suspend0, as requested by Sridhar previously. - Updated the kernel documentation in patch 7 as suggested by Bagas Sanjaya, which improved the htmldoc output. v5: https://lore.kernel.org/netdev/20241103052421.518856-1-jdamato@fastly.com/ - Adjusted patch 5 to only suspend IRQs when ep_send_events returns a positive return value. This issue was pointed out by Hillf Danton. - Updated the commit message of patch 6 which still mentioned netcat, despite the code being updated in v4 to replace it with socat and fixed misspelling of netdevsim. - Fixed a minor typo in patch 7 and removed an unnecessary paragraph. - Added Sridhar Samudrala's Reviewed-by to patch 1-5 and 7. v4: https://lore.kernel.org/netdev/20241102005214.32443-1-jdamato@fastly.com/ - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: https://lore.kernel.org/netdev/20241101004846.32532-1-jdamato@fastly.com/ - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (4): net: Add napi_struct parameter irq_suspend_timeout net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 170 ++++++++- fs/eventpoll.c | 36 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 39 +++ net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 164 +++++++++ tools/testing/selftests/net/busy_poller.c | 328 ++++++++++++++++++ 15 files changed, 790 insertions(+), 7 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dc7c381bb8649e3701ed64f6c3e55316675904d7 -- 2.25.1

1 year

2
7
0 0

[PATCH] selftests/mm: Define PKEY_UNRESTRICTED for pkey_sighandler_tests

by Kevin Brodsky

Commit 6e182dc9f268 ("selftests/mm: Use generic pkey register manipulation") makes use of PKEY_UNRESTRICTED in pkey_sighandler_tests. The macro has been proposed for addition to uapi headers [1], but the patch hasn't landed yet. Define PKEY_UNRESTRICTED in pkey-helpers.h for the time being to fix the build. [1] https://lore.kernel.org/all/20241028090715.509527-2-yury.khrustalev@arm.com/ Fixes: 6e182dc9f268 ("selftests/mm: Use generic pkey register manipulation") Reported-by: Aishwarya TCV <aishwarya.tcv(a)arm.com> Signed-off-by: Kevin Brodsky <kevin.brodsky(a)arm.com> --- Based on arm64 for-next/pkey-signal (49f59573e9e0). --- tools/testing/selftests/mm/pkey-helpers.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index 9ab6a3ee153b..319f5b6b7132 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -112,6 +112,10 @@ void record_pkey_malloc(void *ptr, long size, int prot); #define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) #endif +#ifndef PKEY_UNRESTRICTED +#define PKEY_UNRESTRICTED 0x0 +#endif + #ifndef set_pkey_bits static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags) { -- 2.43.0

1 year

3
5
0 0

[PATCH] selftests: netfilter: Fix the bug of missing return values

by guanjing

Fixed the bug of some functions were missing return values. Fixes: eff3c558bb7e ("netfilter: ctnetlink: support filtering by zone") Signed-off-by: Guan Jing <guanjing(a)cmss.chinamobile.com> --- .../testing/selftests/net/netfilter/conntrack_dump_flush.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index 254ff03297f0..5f827e10717d 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -43,6 +43,8 @@ static int build_cta_tuple_v4(struct nlmsghdr *nlh, int type, mnl_attr_nest_end(nlh, nest_proto); mnl_attr_nest_end(nlh, nest); + + return 0; } static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type, @@ -71,6 +73,8 @@ static int build_cta_tuple_v6(struct nlmsghdr *nlh, int type, mnl_attr_nest_end(nlh, nest_proto); mnl_attr_nest_end(nlh, nest); + + return 0; } static int build_cta_proto(struct nlmsghdr *nlh) @@ -90,6 +94,8 @@ static int build_cta_proto(struct nlmsghdr *nlh) mnl_attr_nest_end(nlh, nest_proto); mnl_attr_nest_end(nlh, nest); + + return 0; } static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh, -- 2.33.0

1 year

1
0
0 0

Some thoughts on Linux benchmarks results & processing

by Konstantin Belov

Hello colleagues, Following up on Tim Bird's presentation "Adding benchmarks results support to KTAP/kselftest", I would like to share some thoughts on kernel benchmarking and kernel performance evaluation. Tim suggested sharing these comments with the wider kselftest community for discussion. The topic of performance evaluation is obviously extremely complex, so I’ve organised my comments into several paragraphs, each of which focuses on a specific aspect. This should make it easier to follow and understand the key points, such as metrics, reference values, results data lake, interpretation of contradictory results, system profiles, analysis and methodology. # Metrics A few remarks on benchmark metrics which were called “values” in the original presentation: - Metrics must be accompanied by standardised units. This standardisation ensures consistency across different tests and environments, simplifying accurate comparisons and analysis. - Each metric should be clearly labelled with its nature or kind (throughput, speed, latency, etc). This classification is essential for proper interpretation of the results and prevents misunderstandings that could lead to incorrect conclusions. - Presentation contains "May also include allowable variance", but variance must be included into the analysis as we deal with statistical calculations and multiple randomised values. - I would like to note that other statistical parameters are also worth including into comparison, like confidence levels, sample size and so on. # Reference Values The concept of "reference values" introduced in the slides could be significantly enhanced by implementing a collaborative, transparent system for data collection and validation. This system could operate as follows: - Data Collection: Any user could submit benchmark results to a centralised and public repository. This would allow for a diverse range of hardware configurations and use cases to be represented. - Vendor Validation: Hardware vendors would have the opportunity to review submitted results pertaining to their products. They could then mark certain results as "Vendor Approved," indicating that the results align with their own testing and expectations. - Community Review: The broader community of users and experts could also review and vote on submitted results. Results that receive substantial positive feedback could be marked as "Community Approved," providing an additional layer of validation. - Automated Validation: Reference values must be checked, validated and supported by multiple sources. This can be done only in an automatic way as those processes are time consuming and require extreme attention to details. - Transparency: All submitted results would need to be accompanied by detailed information about the testing environment, hardware specifications, and methodology used. This would ensure reproducibility and allow others to understand the context of each result. - Trust Building: The combination of vendor and community approval would help establish trust in the reference values. It would mitigate concerns about marketing bias and provide a more reliable basis for performance comparisons. - Accessibility: The system would be publicly accessible, allowing anyone to reference and utilise this data in their own testing and analysis. Implementation of such a system would require careful consideration of governance and funding. A community-driven, non-profit organisation sponsored by multiple stakeholders could be an appropriate model. This structure would help maintain neutrality and avoid potential conflicts of interest. While the specifics of building and managing such a system would need further exploration, this approach could significantly improve the reliability and usefulness of reference values in benchmark testing. It would foster a more collaborative and transparent environment for performance evaluation in the Linux ecosystem as well as attract interested vendors to submit and review results. I’m not very informed about the current state of the community in this field, but I’m sure you know better how exactly this can be done. # Results Data Lake Along with reference values it’s important to collect results on a regular basis as the kernel evolves so results must follow this evolution as well. To do this cloud-based data lake is needed (a self-hosted system will be too expensive from my point of view). This data lake should be able to collect and process incoming data as well as to serve reference values for users. Data processing flow should be quite standard: Collection -> Parsing + Enhancement -> Storage -> Analysis -> Serving. Tim proposed to use file names for reference files, I would like to note that such approach could fail pretty fast if system will collect more and more data and there will rise a need to have more granular and detailed features to identify reference results and this can lead to very long filenames, which will be hard to use. I propose to use UUID4-based identification, which provides very low chances for collision. Those IDs will be keys in the database with all information required for clear identification of relevant results and corresponding details. Moreover this approach can be easily extended on the database side if more data is needed. Yes, UUID4 is not human-readable, but do we need such an option if we have tools, which can provide a better interface? For example, this could be something like: --- request: results-cli search -b "Test Suite D" -v "v1.2.3" -o "Ubuntu 22.04" -t "baseline" -m "response_time>100" response: [ { "id": "550e8400-e29b-41d4-a716-446655440005", "benchmark": "Test Suite A", "version": "v1.2.3", "target_os": "Ubuntu 22.04", "metrics": { "cpu_usage": 70.5, "memory_usage": 2048, "response_time": 120 }, "tags": ["baseline", "v1.0"], "created_at": "2024-10-25T10:00:00Z" }, ... ] --- or request: results-cli search "<Domain-Specific-Language-Query>" response: [ {}, {}, {}...] --- or request: results-cli get 550e8400-e29b-41d4-a716-446655440005 response: { "id": "550e8400-e29b-41d4-a716-446655440005", "benchmark": "Test Suite A", "version": "v1.2.3", "target_os": "Ubuntu 22.04", "metrics": { "cpu_usage": 70.5, "memory_usage": 2048, "response_time": 120 }, "tags": ["baseline", "v1.0"], "created_at": "2024-10-25T10:00:00Z" } --- or request: curl -X POST http://api.example.com/references/search \ -d '{ "query": "benchmark = \"Test Suite A\" AND (version >= \"v1.2\" OR tag IN [\"baseline\", \"regression\"]) AND cpu_usage > 60" }' ... --- Another point of use DB-based approach is the following: in case when a user works with particular hardware and/or would like to use a reference he/she does not need a full database with all collected reference values, but only a small slice of it. This slice can be downloaded from public repo or accessed via API. # Large results dataset If we collect a large benchmarks dataset in one place accompanied with detailed information about target systems from which this dataset was collected, then it will allow us to calculate precise baselines across different compositions of parameters, making performance deviations easier to detect. Long-term trend analysis can identify small changes and correlate them with updates, revealing performance drift. Another use of such a database - predictive modelling, which can provide forecasts of expected results and setting dynamic performance thresholds, enabling early issue detection. Anomaly detection becomes more effective with context, distinguishing unusual deviations from normal behaviour. # Interpretation of contradictory results It’s not clear how to deal with contradictory results to make a decision on regression presence. For example, we have a set of 10 tests, which test more or less the same, for example disk performance. It’s unclear what to do when one subset of tests show degradation and another subset shows neutral status or improvements. Is there a regression? I suppose that the availability of historical data can help to deal with such situations as historical data can show behaviour of particular tests and allow to assign weights in decision-making algorithms, but it’s just my guess. # System Profiles Tim's idea to reduce results to - “pass / fail” and my experience with various people trying to interpret benchmarking results led me to think of “profiles” - a set of parameters and metrics collected from a reference system while execution of a particular configuration of a particular benchmark. Profiles can be used for A/B comparison with pass/fail outcomes or match/not match, and this approach does not hide/miss the details and allows to capture multiple characteristics of the experiment, like presence of outliers/errors or skewed distribution form. Interested persons (like kernel developers or performance engineers, for example) can dig deeper to find a reason for such mismatch and those who are interested just in high-level results - pass/fail should be enough. Here is how I imaging a structure of a profile: --- profile_a: system packages: - pkg_1 - pkg_2 # Additional packages... settings: - cmdline # Additional settings... indicators: cpu: null ram: null loadavg: null # Additional indicators... benchmark: settings: param_1: null param_2: null param_x: null metrics: metric_1: null metric_2: null metric_x: null --- - System Packages, System Settings: Usually we do not pay much attention to this, but I think it’s worth highlighting that base OS is an important factor, as there are distribution-specific modifications present in the filesystem. Most commonly developers and researchers use Ubuntu (as the most popular distro) or Debian (as a cleaner and lightweight version of Ubuntu), but distributions apply their own patches to the kernel and system libraries, which may impact performance. Another kind of base OS - cloud OS images which can be modified by cloud providers to add internal packages & services which could potentially affect performance as well. While comparing we must take into account this aspect to compare apples-to-apples. - System Indicators: These are periodic statistics like CPU utilisation, RAM consumption, and other params collected before benchmarking, while benchmarking and after benchmarking. - Benchmark Settings: Benchmarking systems have multiple parameters, so it’s important to capture them and use them in analysis. - Benchmark Metrics: That’s obviously - benchmark results. It’s not a rare case when a benchmark test provides more than a single number. # Analysis Proposed rules-based analysis will work only for highly determined environments and systems, where rules can describe all the aspects. Rule-based systems are easier to understand and implement than other types, but for a small set of rules. However, we deal with the live system and it constantly evolves, so rules will deprecate extremely fast. It's the same story as with rule-based recommended systems in early years of machine learning. If you want to follow a rules-based approach, it's probably worth taking a look at https://www.clipsrules.net as this will allow to decouple results from analysis and avoid reinventing the analysis engine. Declaration of those rules will be error-prone due to the nature of their origin - they must be declared and maintained by humans. IMHO a human-less approach and use modern ML methods instead would be more beneficial in the long run. # Methodology Used methodology - another aspect which is not directly related to Tim's slides, but it's an important topic for results processing and interpretation, probably an idea of automated results interpretation can force use of one or another methodology. # Next steps I would be glad to participate in further discussions and share experience to improve kernel performance testing automation, analysis and interpretation of results. If there is interest, I'm open to collaborating on implementing some of these ideas. -- Best regards, Konstantin Belov

1 year

2
1
0 0

[PATCH net-next v7 0/6] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v7, see changelog below. This revision drops patch 2 from the previous version, which was unnecessary as Jakub pointed out. The tests were fully re-run after dropping the patch to confirm the performance numbers hold; they do - see below. FAQ #2 has been updated to be more verbose, as well. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Important call out in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspend0: - set defer_hard_irqs to 0 - set gro_flush_timeout to 0 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over nearly 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results shift between submissions, but the relative differences are equivalent. As patches are rebased, several factors likely influence overall performance. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. - suspend0, which sets defer_hard_irqs and gro_flush_timeout to 0, has nearly the same performance as the base case (this is FAQ item #1). The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 199946 112 239 416 26 12973 11343 defer10 200K 199971 54 124 142 29 19412 17460 defer20 200K 199986 60 130 153 26 15644 14095 defer50 200K 200025 79 144 182 23 12122 11632 defer200 200K 199999 164 254 309 19 8923 9635 fullbusy 200K 199998 46 118 133 100 43658 23133 napibusy 200K 199983 100 237 277 56 24840 24716 suspend0 200K 200020 105 249 432 30 14264 11796 suspend10 200K 199950 53 123 141 32 19518 16903 suspend20 200K 200037 58 126 151 30 16426 14736 suspend50 200K 199961 73 136 177 26 13310 12633 suspend200 200K 199998 149 251 306 21 9566 10203 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400014 139 269 707 41 9476 9343 defer10 400K 400016 59 133 166 53 13991 12989 defer20 400K 399952 67 140 172 47 12063 11644 defer50 400K 400007 87 162 198 39 9384 9880 defer200 400K 399979 181 274 330 31 7089 8430 fullbusy 400K 399987 50 123 156 100 21827 16037 napibusy 400K 400014 76 222 272 83 18185 16529 suspend0 400K 400015 127 350 776 47 10699 9603 suspend10 400K 400023 57 129 164 54 13758 13178 suspend20 400K 400043 62 135 169 49 12071 11826 suspend50 400K 400071 76 149 186 42 10011 10301 suspend200 400K 399961 154 269 327 34 7827 8774 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 599951 149 266 574 61 9265 8876 defer10 600K 600006 71 147 203 76 11866 10936 defer20 600K 600123 76 152 203 66 10430 10342 defer50 600K 600162 95 172 217 54 8526 9142 defer200 600K 599942 200 301 357 46 6977 8212 fullbusy 600K 599990 55 127 177 100 14551 13983 napibusy 600K 600035 63 160 250 96 13937 14140 suspend0 600K 599903 127 320 732 68 10166 8963 suspend10 600K 599908 63 137 192 69 10902 11100 suspend20 600K 599961 66 141 194 65 9976 10370 suspend50 600K 599973 80 159 204 57 8678 9381 suspend200 600K 600010 157 277 346 48 7133 8381 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800039 181 300 536 87 9585 8304 defer10 800K 800038 181 530 939 96 10564 8970 defer20 800K 800029 112 225 329 90 10056 8935 defer50 800K 799999 120 208 296 82 9234 8562 defer200 800K 800066 227 338 401 63 7117 8129 fullbusy 800K 800040 61 134 190 100 10913 12608 napibusy 800K 799944 64 141 214 99 10828 12588 suspend0 800K 799911 126 248 509 85 9346 8498 suspend10 800K 800006 69 143 200 83 9410 9845 suspend20 800K 800120 74 150 207 78 8786 9454 suspend50 800K 799989 87 168 224 71 7946 8833 suspend200 800K 799987 160 292 357 62 6923 8229 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 906879 4079 5751 6216 98 9496 7904 defer10 1000K 860849 3643 6274 6730 99 10040 8676 defer20 1000K 896063 3298 5840 6349 98 9620 8237 defer50 1000K 919782 2962 5513 5807 97 9284 7951 defer200 1000K 970941 3059 5348 5984 95 8593 7959 fullbusy 1000K 999950 70 150 207 100 8732 10777 napibusy 1000K 999996 78 154 223 100 8722 10656 suspend0 1000K 949706 2666 5770 6660 99 9071 8046 suspend10 1000K 1000024 80 160 220 92 8137 9035 suspend20 1000K 1000059 83 165 226 89 7850 8804 suspend50 1000K 999955 95 180 240 84 7411 8459 suspend200 1000K 999914 163 299 366 77 6833 8078 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1037654 4184 5453 5810 100 8411 7938 defer10 MAX 905607 4840 6151 6380 100 9639 8431 defer20 MAX 986463 4455 5594 5796 100 8848 8110 defer50 MAX 1077030 4000 5073 5299 100 8104 7920 defer200 MAX 1040728 4152 5385 5765 100 8379 7849 fullbusy MAX 1247536 3518 3935 3984 100 6998 7930 napibusy MAX 1136310 3799 7756 9964 100 7670 7877 suspend0 MAX 1057509 4132 5724 6185 100 8253 7918 suspend10 MAX 1215147 3580 3957 4041 100 7185 7944 suspend20 MAX 1216469 3576 3953 3988 100 7175 7950 suspend50 MAX 1215871 3577 3961 4075 100 7181 7949 suspend200 MAX 1216882 3556 3951 3988 100 7175 7955 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2 can take control from Loop 1, if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2 and 3 "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2, which essentially tilts this in favour of Loop 3. If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3 cannot take control from Loop 1. Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. This is shown in the results above: compare suspend0 with the base case. Note that the lack of napi_defer_hard_irqs and gro_flush_timeout produce similar results for both, which encourages the use of napi_defer_hard_irqs and gro_flush_timeout in addition to irq_suspend_timeout. - Can the new timeout value be threaded through the new epoll ioctl ? It is possible, but presents challenges for userspace. User applications must ensure that the file descriptors added to epoll contexts have the same NAPI ID to support busy polling. An epoll context is not permanently tied to any particular NAPI ID. So, a user application could decide to clear the file descriptors from the context and add a new set of file descriptors with a different NAPI ID to the context. Busy polling would work as expected, but the meaning of the suspend timeout becomes ambiguous because IRQs are not inherently associated with epoll contexts, but rather with the NAPI. The user program would need to reissue the ioctl to set the irq_suspend_timeout, but the napi_defer_hard_irqs and gro_flush_timeout settings would come from the NAPI's napi_config (which are set either by sysfs or by netlink). Such an interface seems awkard to use from a user perspective. Further, IRQs are related to NAPIs, which is why they are stored in the napi_config space. Putting the irq_suspend_timeout in the epoll context while other IRQ deferral mechanisms remain in the NAPI's napi_config space seems like an odd design choice. We've opted to keep all of the IRQ deferral parameters together and place the irq_suspend_timeout in napi_config. This has nice benefits for userspace: if a user app were to remove all file descriptors from an epoll context and add new file descriptors with a new NAPI ID, the correct suspend timeout for that NAPI ID would be used automatically without the user application needing to do anything (like re-issuing an ioctl, for example). All IRQ deferral related parameters are in one place and can all be set the same way: with netlink. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the results. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v7: - Jakub noted that patch 2 adds unnecessary complexity by checking the suspend timeout in the NAPI loop. This makes the code more complicated and difficult to reason about. He's right; we've dropped patch 2 which simplifies this series. - Updated the cover letter with a full re-run of all test cases. - Updated FAQ #2. v6: https://lore.kernel.org/netdev/20241104215542.215919-1-jdamato@fastly.com/ - Updated the cover letter with a full re-run of all test cases, including a new case suspend0, as requested by Sridhar previously. - Updated the kernel documentation in patch 7 as suggested by Bagas Sanjaya, which improved the htmldoc output. v5: https://lore.kernel.org/netdev/20241103052421.518856-1-jdamato@fastly.com/ - Adjusted patch 5 to only suspend IRQs when ep_send_events returns a positive return value. This issue was pointed out by Hillf Danton. - Updated the commit message of patch 6 which still mentioned netcat, despite the code being updated in v4 to replace it with socat and fixed misspelling of netdevsim. - Fixed a minor typo in patch 7 and removed an unnecessary paragraph. - Added Sridhar Samudrala's Reviewed-by to patch 1-5 and 7. v4: https://lore.kernel.org/netdev/20241102005214.32443-1-jdamato@fastly.com/ - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: https://lore.kernel.org/netdev/20241101004846.32532-1-jdamato@fastly.com/ - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (4): net: Add napi_struct parameter irq_suspend_timeout net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 170 ++++++++- fs/eventpoll.c | 36 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 41 +++ net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 164 +++++++++ tools/testing/selftests/net/busy_poller.c | 328 ++++++++++++++++++ 15 files changed, 792 insertions(+), 7 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dc7c381bb8649e3701ed64f6c3e55316675904d7 -- 2.25.1

1 year

1
1
0 0

[PATCH net-next v1 0/7] devmem TCP fixes

by Mina Almasry

A few unrelated devmem TCP fixes bundled in a series for some convenience (if that's ok). Patch 1-2: fix naming and provide page_pool_alloc_netmem for fragged netmem. Patch 3-4: fix issues with dma-buf dma addresses being potentially passed to dma_sync_for_* helpers. Patch 5-6: fix syzbot SO_DEVMEM_DONTNEED issue and add test for this case. Mina Almasry (6): net: page_pool: rename page_pool_alloc_netmem to *_netmems net: page_pool: create page_pool_alloc_netmem page_pool: disable sync for cpu for dmabuf memory provider netmem: add netmem_prefetch net: fix SO_DEVMEM_DONTNEED looping too long ncdevmem: add test for too many token_count Samiullah Khawaja (1): page_pool: Set `dma_sync` to false for devmem memory provider include/net/netmem.h | 7 ++++ include/net/page_pool/helpers.h | 50 ++++++++++++++++++-------- include/net/page_pool/types.h | 2 +- net/core/devmem.c | 9 +++-- net/core/page_pool.c | 11 +++--- net/core/sock.c | 46 ++++++++++++++---------- tools/testing/selftests/net/ncdevmem.c | 11 ++++++ 7 files changed, 93 insertions(+), 43 deletions(-) -- 2.47.0.163.g1226f6d8fa-goog

1 year

3
9
0 0

[PATCH v6 00/10] iommufd: Add vIOMMU infrastructure (Part-2: vDEVICE)

by Nicolin Chen

Following the previous vIOMMU series, this adds another vDEVICE structure, representing the association from an iommufd_device to an iommufd_viommu. This gives the whole architecture a new "v" layer: _______________________________________________________________________ | iommufd (with vIOMMU/vDEVICE) | | _____________ _____________ | | | | | | | | |----------------| vIOMMU |<---| vDEVICE |<------| | | | | | |_____________| | | | | ______ | | _____________ ___|____ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| This vDEVICE object is used to collect and store all vIOMMU-related device information/attributes in a VM. As an initial series for vDEVICE, add only the virt_id to the vDEVICE, which is a vIOMMU specific device ID in a VM: e.g. vSID of ARM SMMUv3, vDeviceID of AMD IOMMU, and vRID of Intel VT-d to a Context Table. This virt_id helps IOMMU drivers to link the vID to a pID of the device against the physical IOMMU instance. This is essential for a vIOMMU-based invalidation, where the request contains a device's vID for a device cache flush, e.g. ATC invalidation. Therefore, with this vDEVICE object, support a vIOMMU-based invalidation, by reusing IOMMUFD_CMD_HWPT_INVALIDATE for a vIOMMU object to flush cache with a given driver data. As for the implementation of the series, add driver support in ARM SMMUv3 for a real world use case. This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p2-v6 (QEMU branch for testing will be provided in Jason's nesting series) Changelog v6 * Fixed kdoc in the uAPI header * Fixed indentations in iommufd.rst * Replaced vdev->idev with vdev->dev * Added "Reviewed-by" from Kevin and Jason * Updated kdoc of struct iommu_vdevice_alloc * Fixed lockdep function call in iommufd_viommu_find_dev * Added missing iommu_dev validation between viommu and idev * Skipped SMMUv3 driver changes (to post in a separate series) * Replaced !cache_invalidate_user in WARN_ON of the allocation path with cache_invalidate_user validation in iommufd_hwpt_invalidate v5 https://lore.kernel.org/all/cover.1729897278.git.nicolinc@nvidia.com/ * Dropped driver-allocated vDEVICE support * Changed vdev_to_dev helper to iommufd_viommu_find_dev v4 https://lore.kernel.org/all/cover.1729555967.git.nicolinc@nvidia.com/ * Added missing brackets in switch-case * Fixed the unreleased idev refcount issue * Reworked the iommufd_vdevice_alloc allocator * Dropped support for IOMMU_VIOMMU_TYPE_DEFAULT * Added missing TEST_LENGTH and fail_nth coverages * Added a verification to the driver-allocated vDEVICE object * Added an iommufd_vdevice_abort for a missing mutex protection * Added a u64 structure arm_vsmmu_invalidation_cmd for user command conversion v3 https://lore.kernel.org/all/cover.1728491532.git.nicolinc@nvidia.com/ * Added Jason's Reviewed-by * Split this invalidation part out of the part-1 series * Repurposed VDEV_ID ioctl to a wider vDEVICE structure and ioctl * Reduced viommu_api functions by allowing drivers to access viommu and vdevice structure directly * Dropped vdevs_rwsem by using xa_lock instead * Dropped arm_smmu_cache_invalidate_user v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Jason Gunthorpe (1): iommu: Add iommu_copy_struct_from_full_user_array helper Nicolin Chen (9): iommufd/viommu: Add IOMMUFD_OBJ_VDEVICE and IOMMU_VDEVICE_ALLOC ioctl iommufd/selftest: Add IOMMU_VDEVICE_ALLOC test coverage iommu/viommu: Add cache_invalidate to iommufd_viommu_ops iommufd: Allow hwpt_id to carry viommu_id for IOMMU_HWPT_INVALIDATE iommufd/viommu: Add iommufd_viommu_find_dev helper iommufd/selftest: Add mock_viommu_cache_invalidate iommufd/selftest: Add IOMMU_TEST_OP_DEV_CHECK_CACHE test command iommufd/selftest: Add vIOMMU coverage for IOMMU_HWPT_INVALIDATE ioctl Documentation: userspace-api: iommufd: Update vDEVICE drivers/iommu/iommufd/iommufd_private.h | 18 ++ drivers/iommu/iommufd/iommufd_test.h | 30 +++ include/linux/iommu.h | 48 ++++- include/linux/iommufd.h | 22 ++ include/uapi/linux/iommufd.h | 31 ++- tools/testing/selftests/iommu/iommufd_utils.h | 83 +++++++ drivers/iommu/iommufd/driver.c | 13 ++ drivers/iommu/iommufd/hw_pagetable.c | 40 +++- drivers/iommu/iommufd/main.c | 6 + drivers/iommu/iommufd/selftest.c | 98 ++++++++- drivers/iommu/iommufd/viommu.c | 76 +++++++ tools/testing/selftests/iommu/iommufd.c | 204 +++++++++++++++++- .../selftests/iommu/iommufd_fail_nth.c | 4 + Documentation/userspace-api/iommufd.rst | 41 +++- 14 files changed, 688 insertions(+), 26 deletions(-) -- 2.43.0

1 year

4
25
0 0

[PATCH v6 00/13] iommufd: Add vIOMMU infrastructure (Part-1)

by Nicolin Chen

This series introduces a new vIOMMU infrastructure and related ioctls. IOMMUFD has been using the HWPT infrastructure for all cases, including a nested IO page table support. Yet, there're limitations for an HWPT-based structure to support some advanced HW-accelerated features, such as CMDQV on NVIDIA Grace, and HW-accelerated vIOMMU on AMD. Even for a multi-IOMMU environment, it is not straightforward for nested HWPTs to share the same parent HWPT (stage-2 IO pagetable), with the HWPT infrastructure alone: a parent HWPT typically hold one stage-2 IO pagetable and tag it with only one ID in the cache entries. When sharing one large stage-2 IO pagetable across physical IOMMU instances, that one ID may not always be available across all the IOMMU instances. In other word, it's ideal for SW to have a different container for the stage-2 IO pagetable so it can hold another ID that's available. And this container will be able to hold some advanced feature too. For this "different container", add vIOMMU, an additional layer to hold extra virtualization information: _______________________________________________________________________ | iommufd (with vIOMMU) | | _____________ | | | | | | |----------------| vIOMMU | | | | ______ | | _____________ ________ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | | | | | | | | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| The vIOMMU object should be seen as a slice of a physical IOMMU instance that is passed to or shared with a VM. That can be some HW/SW resources: - Security namespace for guest owned ID, e.g. guest-controlled cache tags - Non-device-affiliated event reporting, e.g. invalidation queue errors - Access to a sharable nesting parent pagetable across physical IOMMUs - Virtualization of various platforms IDs, e.g. RIDs and others - Delivery of paravirtualized invalidation - Direct assigned invalidation queues - Direct assigned interrupts On a multi-IOMMU system, the vIOMMU object must be instanced to the number of the physical IOMMUs that have a slice passed to (via device) a guest VM, while being able to hold the shareable parent HWPT. Each vIOMMU then just needs to allocate its own individual ID to tag its own cache: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | IDx | ---------------------------- ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested1 |--->| viommu1 ------------------ ---------------- | | IDy | ---------------------------- As an initial part-1, add IOMMUFD_CMD_VIOMMU_ALLOC ioctl for an allocation only. More vIOMMU-based structs and ioctls will be introduced in the follow-up series to support vDEVICE, vIRQ (vEVENT) and vQUEUE objects. Although we repurposed the vIOMMU object from an earlier RFC, just for a referece: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p1-v6 (QEMU branch for testing will be provided in Jason's nesting series) Changelog v6 * Improved comment lines * Added a TEST_F for IO page fault * Fixed indentations in iommufd.rst * Revised kdoc of the viommu_alloc op * Added "Reviewed-by" from Kevin and Jason * Passed in "flags" to ->alloc_domain_nested * Renamed "free" op to "destroy" in viommu_ops * Skipped SMMUv3 driver changes (to post in a separate series) * Fixed "flags" validation in iommufd_viommu_alloc_hwpt_nested * Added CONFIG_IOMMUFD_DRIVER_CORE for sharing between iommufd core and IOMMU dirvers * Replaced iommufd_verify_unfinalized_object with xa_cmpxchg in iommufd_object_finalize/abort functions v5 https://lore.kernel.org/all/cover.1729897352.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Kevin * Reworked iommufd_viommu_alloc helper * Revised the uAPI kdoc for vIOMMU object * Revised comments for pluggable iommu_dev * Added a couple of cleanup patches for selftest * Renamed domain_alloc_nested op to alloc_domain_nested * Updated a few commit messages to reflect the latest series * Renamed iommufd_hwpt_nested_alloc_for_viommu to iommufd_viommu_alloc_hwpt_nested, and added flag validation v4 https://lore.kernel.org/all/cover.1729553811.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Jason * Dropped IOMMU_VIOMMU_TYPE_DEFAULT support * Dropped iommufd_object_alloc_elm renamings * Renamed iommufd's viommu_api.c to driver.c * Reworked iommufd_viommu_alloc helper * Added a separate iommufd_hwpt_nested_alloc_for_viommu function for hwpt_nested allocations on a vIOMMU, and added comparison between viommu->iommu_dev->ops and dev_iommu_ops(idev->dev) * Replaced s2_parent with vsmmu in arm_smmu_nested_domain * Replaced domain_alloc_user in iommu_ops with domain_alloc_nested in viommu_ops * Replaced wait_queue_head_t with a completion, to delay the unplug of mock_iommu_dev * Corrected documentation graph that was missing struct iommu_device * Added an iommufd_verify_unfinalized_object helper to verify driver- allocated vIOMMU/vDEVICE objects * Added missing test cases for TEST_LENGTH and fail_nth v3 https://lore.kernel.org/all/cover.1728491453.git.nicolinc@nvidia.com/ * Rebased on top of Jason's nesting v3 series https://lore.kernel.org/all/0-v3-e2e16cd7467f+2a6a1-smmuv3_nesting_jgg@nvid… * Split the series into smaller parts * Added Jason's Reviewed-by * Added back viommu->iommu_dev * Added support for driver-allocated vIOMMU v.s. core-allocated * Dropped arm_smmu_cache_invalidate_user * Added an iommufd_test_wait_for_users() in selftest * Reworked test code to make viommu an individual FIXTURE * Added missing TEST_LENGTH case for the new ioctl command v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (13): iommufd: Move struct iommufd_object to public iommufd header iommufd: Move _iommufd_object_alloc helper to a sharable file iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct iommufd: Verify object in iommufd_object_finalize/abort() iommufd/viommu: Add IOMMU_VIOMMU_ALLOC ioctl iommufd: Add alloc_domain_nested op to iommufd_viommu_ops iommufd: Allow pt_id to carry viommu_id for IOMMU_HWPT_ALLOC iommufd/selftest: Add container_of helpers iommufd/selftest: Prepare for mock_viommu_alloc_domain_nested() iommufd/selftest: Add refcount to mock_iommu_device iommufd/selftest: Add IOMMU_VIOMMU_TYPE_SELFTEST iommufd/selftest: Add IOMMU_VIOMMU_ALLOC test coverage Documentation: userspace-api: iommufd: Update vIOMMU drivers/iommu/iommufd/Kconfig | 5 + drivers/iommu/iommufd/Makefile | 8 +- drivers/iommu/iommufd/iommufd_private.h | 33 +-- drivers/iommu/iommufd/iommufd_test.h | 2 + include/linux/iommu.h | 14 + include/linux/iommufd.h | 83 ++++++ include/uapi/linux/iommufd.h | 54 +++- tools/testing/selftests/iommu/iommufd_utils.h | 28 ++ drivers/iommu/iommufd/driver.c | 40 +++ drivers/iommu/iommufd/hw_pagetable.c | 72 ++++- drivers/iommu/iommufd/main.c | 54 ++-- drivers/iommu/iommufd/selftest.c | 266 +++++++++++++----- drivers/iommu/iommufd/viommu.c | 81 ++++++ tools/testing/selftests/iommu/iommufd.c | 128 +++++++++ .../selftests/iommu/iommufd_fail_nth.c | 11 + Documentation/userspace-api/iommufd.rst | 69 ++++- 16 files changed, 795 insertions(+), 153 deletions(-) create mode 100644 drivers/iommu/iommufd/driver.c create mode 100644 drivers/iommu/iommufd/viommu.c -- 2.43.0

1 year

3
23
0 0

[PATCH v2 0/2] kselftest/arm64: fp-stress signal delivery interval improvements

by Mark Brown

One of the things that fp-stress does to stress the floating point context switching is send signals to the test threads it spawns. Currently we do this once per second but as suggested by Mark Rutland if we increase this we can improve the chances of triggering any issues with context switching the signal handling code. Do a quick change to increase the rate of signal delivery, trying to avoid excessive impact on emulated platforms, and a further change to mitigate the impact that this creates during startup. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Minor clarifications in commit message and log output. - Link to v1: https://lore.kernel.org/r/20241029-arm64-fp-stress-interval-v1-0-db540abf6d… --- Mark Brown (2): kselftest/arm64: Increase frequency of signal delivery in fp-stress kselftest/arm64: Poll less often while waiting for fp-stress children tools/testing/selftests/arm64/fp/fp-stress.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241028-arm64-fp-stress-interval-8f5e62c06e12 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

3
4
0 0

[PATCH bpf-next 1/2] libbpf: Add missing per-arch include path

by Björn Töpel

From: Björn Töpel <bjorn(a)rivosinc.com> libbpf does not include the per-arch tools include path, e.g. tools/arch/riscv/include. Some architectures depend those files to build properly. Include tools/arch/$(SUBARCH)/include in the libbpf build. Fixes: 6d74d178fe6e ("tools: Add riscv barrier implementation") Signed-off-by: Björn Töpel <bjorn(a)rivosinc.com> --- tools/lib/bpf/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 1b22f0f37288..857a5f7b413d 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -61,7 +61,8 @@ ifndef VERBOSE endif INCLUDES = -I$(or $(OUTPUT),.) \ - -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/arch/$(SRCARCH)/include export prefix libdir src obj base-commit: db5ca265e3334b48c4e3fa07eef79e8bc578c430 -- 2.43.0

1 year

5
11
0 0

[PATCH net-next v9] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- V9: selftests in pmtu.sh: - remove useless return - fix mtu var override V8: selftests in pmtu.sh: - Change var names from "dummy" to "host" - Fix errors caused by incorrect iface arguments pass - Add src addr to setup_multipath_new - Change multipath* func order - Change route_get_dst_exception() && route_get_dst_pmtu_from_exception() and arguments pass where they are used as Ido suggested in https://lore.kernel.org/all/ZykH_fdcMBdFgXix@shredder/ V7: selftest in pmtu.sh: - add setup_multipath() with old and new nh tests - add global "dummy_v4" addr variables - add documentation - remove dummy netdev usage in mp nh test - remove useless sysctl opts in mp nh test V6: - make commit message cleaner V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - add selftest - fix compile error V2: - fix fib_info_num_path parameter pass --- net/ipv4/route.c | 13 ++++ tools/testing/selftests/net/pmtu.sh | 117 ++++++++++++++++++++++++---- 2 files changed, 113 insertions(+), 17 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..652f603d29fe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..611ae7862f46 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -197,6 +197,12 @@ # # - pmtu_ipv6_route_change # Same as above but with IPv6 +# +# - pmtu_ipv4_mp_exceptions +# Use the same topology as in pmtu_ipv4, but add routeable addresses +# on host A and B on lo reachable via both routers. Host A and B +# addresses have multipath routes to each other, b_r1 mtu = 1500. +# Check that PMTU exceptions are created for both paths. source lib.sh source net_helper.sh @@ -266,7 +272,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 1" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a" tunnel6_b_addr="fd00:2::b" tunnel6_mask="64" +host4_a_addr="192.168.99.99" +host4_b_addr="192.168.88.88" + dummy6_0_prefix="fc00:1000::" dummy6_1_prefix="fc00:1001::" dummy6_mask="64" @@ -984,6 +994,52 @@ setup_ovs_bridge() { run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 } +setup_multipath_new() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip nexthop add id 401 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 402 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 403 group 401/402 + run_cmd ${ns_a} ip route add ${host4_b_addr} src ${host4_a_addr} nhid 403 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip nexthop add id 401 via ${prefix4}.${b_r1}.2 dev veth_B-R1 + run_cmd ${ns_b} ip nexthop add id 402 via ${prefix4}.${b_r2}.2 dev veth_B-R2 + run_cmd ${ns_b} ip nexthop add id 403 group 401/402 + run_cmd ${ns_b} ip route add ${host4_a_addr} src ${host4_b_addr} nhid 403 +} + +setup_multipath_old() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip route add ${host4_b_addr} \ + src ${host4_a_addr} \ + nexthop via ${prefix4}.${a_r1}.2 weight 1 \ + nexthop via ${prefix4}.${a_r2}.2 weight 1 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip route add ${host4_a_addr} \ + src ${host4_b_addr} \ + nexthop via ${prefix4}.${b_r1}.2 weight 1 \ + nexthop via ${prefix4}.${b_r2}.2 weight 1 +} + +setup_multipath() { + if [ "$USE_NH" = "yes" ]; then + setup_multipath_new + else + setup_multipath_old + fi + + # Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${host4_a_addr} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_a_addr} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${host4_b_addr} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_b_addr} via ${prefix4}.${b_r2}.1 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -1076,23 +1132,15 @@ link_get_mtu() { } route_get_dst_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" - - if [ -z "${dsfield}" ]; then - dsfield=0 - fi + ns_cmd="${1}"; shift - ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" + ${ns_cmd} ip route get "$@" } route_get_dst_pmtu_from_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "$@")" } check_pmtu_value() { @@ -1235,10 +1283,10 @@ test_pmtu_ipv4_dscp_icmp_exception() { run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -1285,9 +1333,9 @@ test_pmtu_ipv4_dscp_udp_exception() { UDP:"${dst2}":50000,tos="${dsfield}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -2329,6 +2377,41 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing multipath || return $ksft_skip + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + # Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${host4_b_addr}" + + # Do route lookup before checking cached exceptions. + # The following commands are needed for dst entries to be cached + # in both paths exceptions and therefore dumped to user space + # Check that exceptions have been created with the correct PMTU + pmtu_a_R1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R1)" + pmtu_a_R2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R2)" + + check_pmtu_value "1500" "${pmtu_a_R1}" "exceeding MTU (veth_A-R2)" || return 1 + check_pmtu_value "1500" "${pmtu_a_R2}" "exceeding MTU (veth_A-R1)" || return 1 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year

2
1
0 0

[PATCH net-next v8] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- V8: selftests in pmtu.sh: - Change var names from "dummy" to "host" - Fix errors caused by incorrect iface arguments pass - Add src addr to setup_multipath_new - Change multipath* func order - Change route_get_dst_exception() && route_get_dst_pmtu_from_exception() and arguments pass where they are used as Ido suggested in https://lore.kernel.org/all/ZykH_fdcMBdFgXix@shredder/ V7: selftest in pmtu.sh: - add setup_multipath() with old and new nh tests - add global "dummy_v4" addr variables - add documentation - remove dummy netdev usage in mp nh test - remove useless sysctl opts in mp nh test V6: - make commit message cleaner V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - add selftest - fix compile error V2: - fix fib_info_num_path parameter pass --- net/ipv4/route.c | 13 +++ tools/testing/selftests/net/pmtu.sh | 119 ++++++++++++++++++++++++---- 2 files changed, 115 insertions(+), 17 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..652f603d29fe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..2b79a16d3369 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -197,6 +197,12 @@ # # - pmtu_ipv6_route_change # Same as above but with IPv6 +# +# - pmtu_ipv4_mp_exceptions +# Use the same topology as in pmtu_ipv4, but add routeable addresses +# on host A and B on lo reachable via both routers. Host A and B +# addresses have multipath routes to each other, b_r1 mtu = 1500. +# Check that PMTU exceptions are created for both paths. source lib.sh source net_helper.sh @@ -266,7 +272,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 1" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a" tunnel6_b_addr="fd00:2::b" tunnel6_mask="64" +host4_a_addr="192.168.99.99" +host4_b_addr="192.168.88.88" + dummy6_0_prefix="fc00:1000::" dummy6_1_prefix="fc00:1001::" dummy6_mask="64" @@ -984,6 +994,52 @@ setup_ovs_bridge() { run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 } +setup_multipath_new() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip nexthop add id 401 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 402 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 403 group 401/402 + run_cmd ${ns_a} ip route add ${host4_b_addr} src ${host4_a_addr} nhid 403 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip nexthop add id 401 via ${prefix4}.${b_r1}.2 dev veth_B-R1 + run_cmd ${ns_b} ip nexthop add id 402 via ${prefix4}.${b_r2}.2 dev veth_B-R2 + run_cmd ${ns_b} ip nexthop add id 403 group 401/402 + run_cmd ${ns_b} ip route add ${host4_a_addr} src ${host4_b_addr} nhid 403 +} + +setup_multipath_old() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip route add ${host4_b_addr} \ + src ${host4_a_addr} \ + nexthop via ${prefix4}.${a_r1}.2 weight 1 \ + nexthop via ${prefix4}.${a_r2}.2 weight 1 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip route add ${host4_a_addr} \ + src ${host4_b_addr} \ + nexthop via ${prefix4}.${b_r1}.2 weight 1 \ + nexthop via ${prefix4}.${b_r2}.2 weight 1 +} + +setup_multipath() { + if [ "$USE_NH" = "yes" ]; then + setup_multipath_new + else + setup_multipath_old + fi + + # Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${host4_a_addr} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_a_addr} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${host4_b_addr} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_b_addr} via ${prefix4}.${b_r2}.1 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -1076,23 +1132,15 @@ link_get_mtu() { } route_get_dst_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" - - if [ -z "${dsfield}" ]; then - dsfield=0 - fi + ns_cmd="${1}"; shift - ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" + ${ns_cmd} ip route get "$@" } route_get_dst_pmtu_from_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "$@")" } check_pmtu_value() { @@ -1235,10 +1283,10 @@ test_pmtu_ipv4_dscp_icmp_exception() { run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -1285,9 +1333,9 @@ test_pmtu_ipv4_dscp_udp_exception() { UDP:"${dst2}":50000,tos="${dsfield}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -2329,6 +2377,43 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing multipath || return $ksft_skip + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + # Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${host4_b_addr}" + + # Do route lookup before checking cached exceptions. + # The following commands are needed for dst entries to be cached + # in both paths exceptions and therefore dumped to user space + # Check that exceptions have been created with the correct PMTU + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R1)" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R2)" + + check_pmtu_value "1500" "${pmtu}" "exceeding MTU (veth_A-R2)" || return 1 + check_pmtu_value "1500" "${pmtu}" "exceeding MTU (veth_A-R1)" || return 1 + + return ${fail} +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year

3
3
0 0

[PATCH] selftests: vDSO: Do not rely on $ARCH for vdso_test_getrandom && vdso_test_chacha

by Christophe Leroy

$ARCH is not always enough to know whether getrandom vDSO is supported or not. For instance on x86 we want it for x86_64 but not i386. On the other hand, we already have detailed architecture selection in vdso_config.h, the only difference is that it cannot be used for Makefile. But most selftests are built regardless of whether a functionality is supported or not. The return value KSFT_SKIP is there for than: it tells the test is skipped because it is not supported. Make the implementation more flexible by setting a VDSO_GETRANDOM macro in vdso_config.h. That macro contains the path to the file that defines __arch_chacha20_blocks_nostack(). It avoids the symbolic link to vdso directory and will allow architectures to have several implementations of __arch_chacha20_blocks_nostack() if needed. Then restore the original behaviour which was dedicated to vdso_standalone_test_x86 and build getrandom and chacha tests all the time just like other vDSO selftests and return SKIP when the functionality to be tested is not implemented. This has the advantage of doing architecture specific selection at only one place. Also change vdso_test_getrandom to return SKIP instead of FAIL when vDSO function is not found, just like vdso_test_getcpu or vdso_test_gettimeofday. Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- Based on latest random tree (0dfed8092247) tools/arch/x86/vdso | 1 - tools/testing/selftests/vDSO/Makefile | 10 ++++------ tools/testing/selftests/vDSO/vdso_config.h | 3 +++ tools/testing/selftests/vDSO/vdso_test_chacha-asm.S | 7 +++++++ tools/testing/selftests/vDSO/vdso_test_chacha.c | 11 +++++++++++ tools/testing/selftests/vDSO/vdso_test_getrandom.c | 2 +- 6 files changed, 26 insertions(+), 8 deletions(-) delete mode 120000 tools/arch/x86/vdso create mode 100644 tools/testing/selftests/vDSO/vdso_test_chacha-asm.S diff --git a/tools/arch/x86/vdso b/tools/arch/x86/vdso deleted file mode 120000 index 7eb962fd3454..000000000000 --- a/tools/arch/x86/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/x86/entry/vdso/ \ No newline at end of file diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 5ead6b1f0478..cfb7c281b22c 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -ARCH ?= $(shell uname -m | sed -e s/i.86/x86/) -SRCARCH := $(subst x86_64,x86,$(ARCH)) +uname_M := $(shell uname -m 2>/dev/null || echo not) +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) TEST_GEN_PROGS := vdso_test_gettimeofday TEST_GEN_PROGS += vdso_test_getcpu @@ -10,10 +10,8 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness -ifeq ($(ARCH),$(filter $(ARCH),x86_64)) TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha -endif CFLAGS := -std=gnu99 @@ -38,8 +36,8 @@ $(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \ $(KHDR_INCLUDES) \ -isystem $(top_srcdir)/include/uapi -$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/tools/arch/$(SRCARCH)/vdso/vgetrandom-chacha.S +$(OUTPUT)/vdso_test_chacha: vdso_test_chacha-asm.S $(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \ - -idirafter $(top_srcdir)/arch/$(SRCARCH)/include \ + -idirafter $(top_srcdir)/arch/$(ARCH)/include \ -idirafter $(top_srcdir)/include \ -D__ASSEMBLY__ -Wa,--noexecstack diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h index 740ce8c98d2e..693920471160 100644 --- a/tools/testing/selftests/vDSO/vdso_config.h +++ b/tools/testing/selftests/vDSO/vdso_config.h @@ -47,6 +47,7 @@ #elif defined(__x86_64__) #define VDSO_VERSION 0 #define VDSO_NAMES 1 +#define VDSO_GETRANDOM "../../../../arch/x86/entry/vdso/vgetrandom-chacha.S" #elif defined(__riscv__) || defined(__riscv) #define VDSO_VERSION 5 #define VDSO_NAMES 1 @@ -58,6 +59,7 @@ #define VDSO_NAMES 1 #endif +#ifndef __ASSEMBLY__ static const char *versions[7] = { "LINUX_2.6", "LINUX_2.6.15", @@ -88,5 +90,6 @@ static const char *names[2][7] = { "__vdso_getrandom", }, }; +#endif #endif /* __VDSO_CONFIG_H__ */ diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha-asm.S b/tools/testing/selftests/vDSO/vdso_test_chacha-asm.S new file mode 100644 index 000000000000..8e704165f6f2 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_test_chacha-asm.S @@ -0,0 +1,7 @@ +#include "vdso_config.h" + +#ifdef VDSO_GETRANDOM + +#include VDSO_GETRANDOM + +#endif diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index 3a5a08d857cf..9d18d49a82f8 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -8,6 +8,8 @@ #include <string.h> #include <stdint.h> #include <stdbool.h> +#include <linux/kconfig.h> +#include "vdso_config.h" #include "../kselftest.h" static uint32_t rol32(uint32_t word, unsigned int shift) @@ -57,6 +59,10 @@ typedef uint32_t u32; typedef uint64_t u64; #include <vdso/getrandom.h> +#ifdef VDSO_GETRANDOM +#define HAVE_VDSO_GETRANDOM 1 +#endif + int main(int argc, char *argv[]) { enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 }; @@ -68,6 +74,11 @@ int main(int argc, char *argv[]) ksft_print_header(); ksft_set_plan(1); + if (!__is_defined(HAVE_VDSO_GETRANDOM)) { + printf("__arch_chacha20_blocks_nostack() not implemented\n"); + return KSFT_SKIP; + } + for (unsigned int trial = 0; trial < TRIALS; ++trial) { if (getrandom(key, sizeof(key), 0) != sizeof(key)) { printf("getrandom() failed!\n"); diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 8866b65a4605..47ee94b32617 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -115,7 +115,7 @@ static void vgetrandom_init(void) vgrnd.fn = (__typeof__(vgrnd.fn))vdso_sym(version, name); if (!vgrnd.fn) { printf("%s is missing!\n", name); - exit(KSFT_FAIL); + exit(KSFT_SKIP); } ret = VDSO_CALL(vgrnd.fn, 5, NULL, 0, 0, &vgrnd.params, ~0UL); if (ret == -ENOSYS) { -- 2.44.0

1 year

5
15
0 0

[PATCH net-next] selftests: wireguards: use nft by default

by Hangbin Liu

Use nft by default if it's supported, as nft is the replacement for iptables, which is used by default in some releases. Additionally, iptables is dropped in some releases. Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- CC nft developers to see if there are any easier configurations, as I'm not very familiar with nft commands. --- tools/testing/selftests/wireguard/netns.sh | 63 ++++++++++++++++++---- 1 file changed, 53 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..4e29c1a7003c 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -44,6 +44,7 @@ sleep() { read -t "$1" -N 1 || true; } waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } +use_nft() { nft --version &> /dev/null; } cleanup() { set +e @@ -196,13 +197,23 @@ ip1 link set wg0 mtu 1300 ip2 link set wg0 mtu 1300 n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 -n0 iptables -A INPUT -m length --length 1360 -j DROP +if use_nft; then + n0 nft add table inet filter + n0 nft add chain inet filter INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule inet filter INPUT meta length 1360 counter drop +else + n0 iptables -A INPUT -m length --length 1360 -j DROP +fi n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 n2 ping -c 1 -W 1 -s 1269 192.168.241.1 n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 -n0 iptables -F INPUT +if use_nft; then + n0 nft delete table inet filter +else + n0 iptables -F INPUT +fi ip1 link set wg0 mtu $orig_mtu ip2 link set wg0 mtu $orig_mtu @@ -334,7 +345,13 @@ waitiface $netns2 veths n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' -n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +if use_nft; then + n0 nft add table inet nat + n0 nft add chain inet nat POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n0 nft add rule inet nat POSTROUTING ip saddr 192.168.1.0/24 ip daddr 10.0.0.0/24 counter snat to 10.0.0.1 +else + n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +fi n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 n1 ping -W 1 -c 1 192.168.241.2 @@ -348,10 +365,20 @@ n1 wg set wg0 peer "$pub2" persistent-keepalive 0 # Test that sk_bound_dev_if works n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # What about when the mark changes and the packet must be rerouted? -n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft add table inet mangle + n1 nft add chain inet mangle OUTPUT { type route hook output priority mangle\; policy accept \; } + n1 nft add rule inet mangle OUTPUT counter meta mark set 0x1 +else + n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +fi n1 ping -c 1 -W 1 192.168.241.2 # First the boring case n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case -n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft delete table inet mangle +else + n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +fi # Test that onion routing works, even when it loops n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 @@ -385,16 +412,32 @@ n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 # Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. -n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 -n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +if use_nft; then + n2 nft add table inet nat + n2 nft add chain inet nat POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n2 nft add rule inet nat POSTROUTING ip saddr 10.0.0.0/24 ip daddr 192.168.241.0/24 counter snat to 192.168.241.2 + + n0 nft add table inet filter + n0 nft add chain inet filter INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule inet filter INPUT iifname "vethrs" ip saddr != 10.0.0.0/24 counter drop +else + n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 + n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +fi n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' ip0 -4 route add 192.168.241.1 via 10.0.0.100 n2 wg set wg0 peer "$pub1" remove [[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] -n0 iptables -t nat -F -n0 iptables -t filter -F -n2 iptables -t nat -F +if use_nft; then + n0 nft delete table inet nat + n0 nft delete table inet filter + n2 nft delete table inet nat +else + n0 iptables -t nat -F + n0 iptables -t filter -F + n2 iptables -t nat -F +fi ip0 link del vethrc ip0 link del vethrs ip1 link del wg0 -- 2.46.0

1 year

2
1
0 0

[PATCH v2 net-next 0/2] ipv6: fix hangup on device removal

by Paolo Abeni

This addresses the infamous unregister_netdevice splat in net selftests; the actual fix is carried by the first patch, while the 2nd one addresses a related problem in the relevant test that was patially hiding the problem. Targeting net-next as the issue is quite old and I feel a little lost in the fib info/nh jungle. --- v1 -> v2: - drop unintended whitespace change in patch 1/2 Paolo Abeni (2): ipv6: release nexthop on device removal selftests: net: really check for bg process completion net/ipv6/route.c | 6 +++--- tools/testing/selftests/net/pmtu.sh | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) -- 2.45.2

1 year

4
7
0 0

[PATCH v4 0/2] kselftest: tmpfs: Add ksft macros and skip if no root

by Shivam Chaudhary

This version 4 patch series replace direct error handling methods with ksft macros, which provide better reporting.Currently, when the tmpfs test runs, it does not display any output if it passes,and if it fails (particularly when not run as root),it simply exits without any warning or message. This series of patch adds: 1. Add 'ksft_print_header()' and 'ksft_set_plan()' to structure test outputs more effectively. 2. Skip if not run as root. 3. Replace direct error handling with 'ksft_test_result_*', 'ksft_print_msg' and KSFT_SKIP macros for better reporting. v3->v4: - Start a patchset - Split patch into smaller pathes to make it easy to review. Patch1 Replace 'ksft_test_result_skip' with 'KSFT_SKIP' during root run check. Patch2 Replace 'ksft_test_result_fail' with 'KSFT_SKIP' where fail does not make sense, or failure could be due to not unsupported APIs with appropriate warnings. v3: https://lore.kernel.org/all/20241028185756.111832-1-cvam0000@gmail.com/ v2->v3: - Remove extra ksft_set_plan() - Remove function for unshare() - Fix the comment style v2: https://lore.kernel.org/all/20241026191621.2860376-1-cvam0000@gmail.com/ v1->v2: - Make the commit message more clear. v1: https://lore.kernel.org/all/20241024200228.1075840-1-cvam0000@gmail.com/T/#u thanks Shivam Shivam Chaudhary (2): selftests:tmpfs: Add Skip test if not run as root selftests:tmpfs: Add kselftest support to tmpfs .../selftests/tmpfs/bug-link-o-tmpfile.c | 79 +++++++++++++++---- 1 file changed, 62 insertions(+), 17 deletions(-) -- 2.45.2

1 year

2
4
0 0

[PATCH net-next v7] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- V7: selftest in pmtu.sh: - add setup_multipath() with old and new nh tests - add global "dummy_v4" addr variables - add documentation - remove dummy netdev usage in mp nh test - remove useless sysctl opts in mp nh test V6: - make commit message cleaner V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - add selftest - fix compile error V2: - fix fib_info_num_path parameter pass --- net/ipv4/route.c | 13 ++++ tools/testing/selftests/net/pmtu.sh | 95 ++++++++++++++++++++++++++++- 2 files changed, 107 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..652f603d29fe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..f24c84184c61 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -197,6 +197,12 @@ # # - pmtu_ipv6_route_change # Same as above but with IPv6 +# +# - pmtu_ipv4_mp_exceptions +# Use the same topology as in pmtu_ipv4, but add routeable "dummy" +# addresses on host A and B on lo0 reachable via both routers. +# Host A and B "dummy" addresses have multipath routes to each other. +# Check that PMTU exceptions are created for both paths. source lib.sh source net_helper.sh @@ -266,7 +272,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 1" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a" tunnel6_b_addr="fd00:2::b" tunnel6_mask="64" +dummy4_a_addr="192.168.99.99" +dummy4_b_addr="192.168.88.88" + dummy6_0_prefix="fc00:1000::" dummy6_1_prefix="fc00:1001::" dummy6_mask="64" @@ -984,6 +994,50 @@ setup_ovs_bridge() { run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 } +setup_multipath() { + if [ "$USE_NH" = "yes" ]; then + setup_multipath_new + else + setup_multipath_old + fi + + # Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${dummy4_a_addr} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy4_a_addr} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${dummy4_b_addr} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy4_b_addr} via ${prefix4}.${b_r2}.1 +} + +setup_multipath_new() { + # Set up host A with multipath routes to host B dummy4_b_addr + run_cmd ${ns_a} ip addr add ${dummy4_a_addr} dev lo0 + run_cmd ${ns_a} ip nexthop add id 201 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 202 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 203 group 201/202 + run_cmd ${ns_a} ip route add ${dummy4_b_addr} nhid 203 + + # Set up host B with multipath routes to host A dummy4_a_addr + run_cmd ${ns_b} ip addr add ${dummy4_b_addr} dev lo0 + run_cmd ${ns_b} ip nexthop add id 201 via ${prefix4}.${b_r1}.2 dev veth_A-R1 + run_cmd ${ns_b} ip nexthop add id 202 via ${prefix4}.${b_r2}.2 dev veth_A-R2 + run_cmd ${ns_b} ip nexthop add id 203 group 201/202 + run_cmd ${ns_b} ip route add ${dummy4_a_addr} nhid 203 +} + +setup_multipath_old() { + # Set up host A with multipath routes to host B dummy4_b_addr + run_cmd ${ns_a} ip addr add ${dummy4_a_addr} dev lo0 + run_cmd ${ns_a} ip route add ${dummy4_b_addr} \ + nexthop via ${prefix4}.${a_r1}.2 weight 1 \ + nexthop via ${prefix4}.${a_r2}.2 weight 1 + + # Set up host B with multipath routes to host A dummy4_a_addr + run_cmd ${ns_b} ip addr add ${dummy4_b_addr} dev lo0 + run_cmd ${ns_a} ip route add ${dummy4_a_addr} \ + nexthop via ${prefix4}.${a_b1}.2 weight 1 \ + nexthop via ${prefix4}.${a_b2}.2 weight 1 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -2329,6 +2383,45 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing multipath || return $ksft_skip + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + # Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${dummy4_b_addr}" + + # Do route lookup before checking cached exceptions. + # The following commands are needed for dst entries to be cached + # in both paths exceptions and therefore dumped to user space + run_cmd ${ns_a} ip route get ${dummy4_b_addr} oif veth_A-R1 + run_cmd ${ns_a} ip route get ${dummy4_b_addr} oif veth_A-R2 + + # Check cached exceptions + if [ "$(${ns_a} ip -oneline route list cache | grep mtu | wc -l)" -ne 2 ]; then + err " there are not enough cached exceptions" + fail=1 + fi + + return ${fail} +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year

3
3
0 0

[PATCH 0/6] kselftest/arm64: Test floating point signal context restore in fp-stress

by Mark Brown

Currently we test signal delivery to the programs run by fp-stress but our signal handlers simply count the number of signals seen and don't do anything with the floating point state. The original fpsimd-test and sve-test programs had signal handlers called irritators which modify the live register state, verifying that we restore the signal context on return, but a combination of misleading comments and code resulted in them never being used and the equivalent handlers in the other tests being stubbed or omitted. Clarify the code, implement effective irritator handlers for the test programs that can have them and then switch the signals generated by the fp-stress program over to use the irritators, ensuring that we validate that we restore the saved signal context properly. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (6): kselftest/arm64: Correct misleading comments on fp-stress irritators kselftest/arm64: Remove unused ADRs from irritator handlers kselftest/arm64: Corrupt P15 in the irritator when testing SSVE kselftest/arm64: Implement irritators for ZA and ZT kselftest/arm64: Provide a SIGUSR1 handler in the kernel mode FP stress test kselftest/arm64: Test signal handler state modification in fp-stress tools/testing/selftests/arm64/fp/fp-stress.c | 2 +- tools/testing/selftests/arm64/fp/fpsimd-test.S | 4 +--- tools/testing/selftests/arm64/fp/kernel-test.c | 4 ++++ tools/testing/selftests/arm64/fp/sve-test.S | 6 ++---- tools/testing/selftests/arm64/fp/za-test.S | 13 ++++--------- tools/testing/selftests/arm64/fp/zt-test.S | 13 ++++--------- 6 files changed, 16 insertions(+), 26 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241023-arm64-fp-stress-irritator-5415fe92adef Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year

2
15
0 0

Re: [PATCH v2 2/9] initramfs_test: kunit tests for initramfs unpacking

by David Disseldorp

[adding kunit lists to cc, see lore link below for context] https://lore.kernel.org/linux-fsdevel/20241104141750.16119-3-ddiss@suse.de/ On Wed, 6 Nov 2024 07:04:21 +0800, kernel test robot wrote: ... > All warnings (new ones prefixed by >>, old ones prefixed by <<): > > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x0 (section: .data) -> initramfs_test_extract (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x30 (section: .data) -> initramfs_test_fname_overrun (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x60 (section: .data) -> initramfs_test_data (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0x90 (section: .data) -> initramfs_test_csum (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0xc0 (section: .data) -> initramfs_test_hardlink (section: .init.text) > >> WARNING: modpost: vmlinux: section mismatch in reference: initramfs_test_cases+0xf0 (section: .data) -> initramfs_test_many (section: .init.text) If I understand correctly, the kunit_case initramfs_test_cases[] members can't be flagged __initdata, as they need to be present post-init for results queries via debugfs. The remaining -Wimplicit-function-declaration reports are all valid. I'll fix them in v3. Thanks, David

1 year

1
0
0 0

[PATCH] selftests/ftrace: update kprobe syntax error test for ppc64le

by Hari Bathini

For ppc64le, depending on the kernel configuration used, offset 16 from function start address can also be considered function entry. Update the test case to accommodate such configurations. Signed-off-by: Hari Bathini <hbathini(a)linux.ibm.com> --- .../selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc index a16c6a6f6055..c03b94cc5784 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc @@ -111,7 +111,11 @@ check_error 'p vfs_read $arg* ^$arg*' # DOUBLE_ARGS if !grep -q 'kernel return probes support:' README; then check_error 'r vfs_read ^$arg*' # NOFENTRY_ARGS fi +if [ "$(uname -m)" = "ppc64le" ]; then +check_error 'p vfs_read+20 ^$arg*' # NOFENTRY_ARGS +else check_error 'p vfs_read+8 ^$arg*' # NOFENTRY_ARGS +fi check_error 'p vfs_read ^hoge' # NO_BTFARG check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters) check_error 'r kfree ^$retval' # NO_RETVAL -- 2.47.0

1 year, 1 month

4
14
0 0

[PATCH net-next] selftests: net: include lib/sh/*.sh with lib.sh

by Matthieu Baerts (NGI0)

Recently, the net/lib.sh file has been modified to include defer.sh from net/lib/sh/ directory. The Makefile from net/lib has been modified accordingly, but not the ones from the sub-targets using net/lib.sh. Because of that, the new file is not installed as expected when installing the Forwarding, MPTCP, and Netfilter targets, e.g. # make -C tools/testing/selftests TARGETS=net/mptcp install \ INSTALL_PATH=/tmp/kself # cd /tmp/kself/ # ./run_kselftest.sh -c net/mptcp TAP version 13 1..7 # timeout set to 1800 # selftests: net/mptcp: mptcp_connect.sh # ./../lib.sh: line 5: /tmp/kself/net/lib/sh/defer.sh: No such file or directory # (...) This can be fixed simply by adding all the .sh files from net/lib/sh directory to the TEST_INCLUDES variable in the different Makefile's. Fixes: a6e263f125cd ("selftests: net: lib: Introduce deferred commands") Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- tools/testing/selftests/net/forwarding/Makefile | 3 ++- tools/testing/selftests/net/mptcp/Makefile | 2 +- tools/testing/selftests/net/netfilter/Makefile | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 224346426ef2220470bf2dbef66198eae9331f56..7d885cff8d79bc6882d2341d0a1a59891fc1cb2e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -126,6 +126,7 @@ TEST_FILES := devlink_lib.sh \ tc_common.sh TEST_INCLUDES := \ - ../lib.sh + ../lib.sh \ + $(wildcard ../lib/sh/*.sh) include ../../lib.mk diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 5d796622e73099d0a0331c1bc8a41f09e1d36b4d..8e3fc05a539797c5e0feab72be69db623ef3fa96 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -11,7 +11,7 @@ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq TEST_FILES := mptcp_lib.sh settings -TEST_INCLUDES := ../lib.sh ../net_helper.sh +TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 542f7886a0bc2ac016f41d8b70357a8e0c1d271b..9d009f74cfc2da66428b1e23d5884e2c3bc4a85d 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -55,4 +55,5 @@ TEST_FILES := lib.sh TEST_FILES += packetdrill TEST_INCLUDES := \ - ../lib.sh + ../lib.sh \ + $(wildcard ../lib/sh/*.sh) --- base-commit: ecf99864ea6b1843773589a935bb026951bf12dd change-id: 20241104-net-next-selftests-lib-sh-deps-cc359ca5602f Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 1 month

3
2
0 0

[PATCH bpf-next/net v3] selftests/bpf: Drop netns helpers in mptcp

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> New netns selftest helpers netns_new() and netns_free() has been added in network_helpers.c, let's use them in mptcp selftests too instead of using MPTCP's own helpers create_netns() and cleanup_netns(). Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- v3: - No code has changed. - Change subject prefix as "bpf-next/net" since CI complains that this patch cannot be merged. - Add Matt's Reviewed-by tag. v2: - Use netns_new/netns_free instead of create_netns/cleanup_netns as Martin suggested. v1: selftests/bpf: Use make/remove netns helpers in mptcp --- .../testing/selftests/bpf/prog_tests/mptcp.c | 42 ++++++------------- 1 file changed, 12 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index be3cad2aff77..f8eb7f9d4fd2 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -69,24 +69,6 @@ struct mptcp_storage { char ca_name[TCP_CA_NAME_MAX]; }; -static struct nstoken *create_netns(void) -{ - SYS(fail, "ip netns add %s", NS_TEST); - SYS(fail, "ip -net %s link set dev lo up", NS_TEST); - - return open_netns(NS_TEST); -fail: - return NULL; -} - -static void cleanup_netns(struct nstoken *nstoken) -{ - if (nstoken) - close_netns(nstoken); - - SYS_NOFAIL("ip netns del %s", NS_TEST); -} - static int start_mptcp_server(int family, const char *addr_str, __u16 port, int timeout_ms) { @@ -206,15 +188,15 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp) static void test_base(void) { - struct nstoken *nstoken = NULL; + struct netns_obj *netns = NULL; int server_fd, cgroup_fd; cgroup_fd = test__join_cgroup("/mptcp"); if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new")) goto fail; /* without MPTCP */ @@ -237,7 +219,7 @@ static void test_base(void) close(server_fd); fail: - cleanup_netns(nstoken); + netns_free(netns); close(cgroup_fd); } @@ -322,21 +304,21 @@ static int run_mptcpify(int cgroup_fd) static void test_mptcpify(void) { - struct nstoken *nstoken = NULL; + struct netns_obj *netns = NULL; int cgroup_fd; cgroup_fd = test__join_cgroup("/mptcpify"); if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new")) goto fail; ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify"); fail: - cleanup_netns(nstoken); + netns_free(netns); close(cgroup_fd); } @@ -414,7 +396,7 @@ static void run_subflow(void) static void test_subflow(void) { struct mptcp_subflow *skel; - struct nstoken *nstoken; + struct netns_obj *netns; int cgroup_fd; cgroup_fd = test__join_cgroup("/mptcp_subflow"); @@ -437,8 +419,8 @@ static void test_subflow(void) if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow")) goto skel_destroy; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_subflow")) goto skel_destroy; if (endpoint_init("subflow") < 0) @@ -447,7 +429,7 @@ static void test_subflow(void) run_subflow(); close_netns: - cleanup_netns(nstoken); + netns_free(netns); skel_destroy: mptcp_subflow__destroy(skel); close_cgroup: -- 2.45.2

1 year, 1 month

2
1
0 0

[PATCH net-next v1 0/7] devmem TCP fixes

by Mina Almasry

A few unrelated devmem TCP fixes bundled in a series for some convenience (if that's ok). Patch 1-2: fix naming and provide page_pool_alloc_netmem for fragged netmem. Patch 3-4: fix issues with dma-buf dma addresses being potentially passed to dma_sync_for_* helpers. Patch 5-6: fix syzbot SO_DEVMEM_DONTNEED issue and add test for this case. Mina Almasry (6): net: page_pool: rename page_pool_alloc_netmem to *_netmems net: page_pool: create page_pool_alloc_netmem page_pool: disable sync for cpu for dmabuf memory provider netmem: add netmem_prefetch net: fix SO_DEVMEM_DONTNEED looping too long ncdevmem: add test for too many token_count Samiullah Khawaja (1): page_pool: Set `dma_sync` to false for devmem memory provider include/net/netmem.h | 7 ++++ include/net/page_pool/helpers.h | 50 ++++++++++++++++++-------- include/net/page_pool/types.h | 2 +- net/core/devmem.c | 9 +++-- net/core/page_pool.c | 11 +++--- net/core/sock.c | 46 ++++++++++++++---------- tools/testing/selftests/net/ncdevmem.c | 11 ++++++ 7 files changed, 93 insertions(+), 43 deletions(-) -- 2.47.0.163.g1226f6d8fa-goog

1 year, 1 month

3
12
0 0

[PATCH v5 0/2] selftests/resctrl: SNC kernel support discovery

by Maciej Wieczor-Retman

Changes v5: - Tests are skipped if snc_unreliable was set. - Moved resctrlfs.c changes from patch 2/2 to 1/2. - Removed CAT changes since it's not impacted by SNC in the selftest. - Updated various comments. - Fixed a bunch of minor issues pointed out in the review. Changes v4: - Printing SNC warnings at the start of every test. - Printing SNC warnings at the end of every relevant test. - Remove global snc_mode variable, consolidate snc detection functions into one. - Correct minor mistakes. Changes v3: - Reworked patch 2. - Changed minor things in patch 1 like function name and made corrections to the patch message. Changes v2: - Removed patches 2 and 3 since now this part will be supported by the kernel. Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory into multiple NUMA nodes. When enabled, NUMA-aware applications can achieve better performance on bigger server platforms. SNC support in the kernel was merged into x86/cache [1]. With SNC enabled and kernel support in place all the tests will function normally (aside from effective cache size). There might be a problem when SNC is enabled but the system is still using an older kernel version without SNC support. Currently the only message displayed in that situation is a guess that SNC might be enabled and is causing issues. That message also is displayed whenever the test fails on an Intel platform. Add a mechanism to discover kernel support for SNC which will add more meaning and certainty to the error message. Add runtime SNC mode detection and verify how reliable that information is. Series was tested on Ice Lake server platforms with SNC disabled, SNC-2 and SNC-4. The tests were also ran with and without kernel support for SNC. Series applies cleanly on kselftest/next. [1] https://lore.kernel.org/all/20240628215619.76401-1-tony.luck@intel.com/ Previous versions of this series: [v1] https://lore.kernel.org/all/cover.1709721159.git.maciej.wieczor-retman@inte… [v2] https://lore.kernel.org/all/cover.1715769576.git.maciej.wieczor-retman@inte… [v3] https://lore.kernel.org/all/cover.1719842207.git.maciej.wieczor-retman@inte… [v4] https://lore.kernel.org/all/cover.1720774981.git.maciej.wieczor-retman@inte… Maciej Wieczor-Retman (2): selftests/resctrl: Adjust effective L3 cache size with SNC enabled selftests/resctrl: Adjust SNC support messages tools/testing/selftests/resctrl/cmt_test.c | 8 +- tools/testing/selftests/resctrl/mba_test.c | 8 +- tools/testing/selftests/resctrl/mbm_test.c | 10 +- tools/testing/selftests/resctrl/resctrl.h | 7 + .../testing/selftests/resctrl/resctrl_tests.c | 8 +- tools/testing/selftests/resctrl/resctrlfs.c | 132 ++++++++++++++++++ 6 files changed, 166 insertions(+), 7 deletions(-) -- 2.46.2

1 year, 1 month

2
5
0 0

[PATCH net-next v6 0/7] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v6, see changelog below. This revision includes only documentation changes: patch 7 has been updated with Bagas' suggestions and the htmldoc looks better as a result. In addition, this cover letter has been updated with a full re-run of the test data. We've included a new test case highlighting a case Sridhar asked about in our v3. See below. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. We've added an additional test case, 'fullbusy', achieved by modifying libevent for comparison. See below for a detailed description, link to the patch, and test results. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Design rationale The implementation of the IRQ suspension mechanism very nicely dovetails with the existing mechanism for IRQ deferral when preferred busy poll is enabled (introduced in commit 7fd3253a7de6 ("net: Introduce preferred busy-polling"), see that commit message for more details). While it would be possible to inject the suspend timeout via the existing epoll ioctl, it is more natural to avoid this path for one main reason: An epoll context is linked to NAPI IDs as file descriptors are added; this means any epoll context might suddenly be associated with a different net_device if the application were to replace all existing fds with fds from a different device. In this case, the scope of the suspend timeout becomes unclear and many edge cases for both the user application and the kernel are introduced Only a single iteration through napi busy polling is needed for this mechanism to work effectively. Since an important objective for this mechanism is preserving cpu cycles, exactly one iteration of the napi busy loop is invoked when busy_poll_usecs is set to 0. ~ Important call out in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspend0: - set defer_hard_irqs to 0 - set gro_flush_timeout to 0 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over at least 15 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results are higher than our previous submission, but the relative differences between variants are equivalent. Because the patches have been rebased on 6.12, several factors have likely influenced the overall performance. Most importantly, we had to switch to a new set of basic kernel options, which has likely altered the baseline performance. Because the overall comparison of variants still holds, we have not attempted to recreate the exact set of kernel options from the previous submission. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. - suspend0, which sets defer_hard_irqs and gro_flush_timeout to 0, has nearly the same performance as the base case (this is FAQ item #1). The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 199954 112 237 415 26 13040 11336 defer10 200K 200002 54 123 142 28 19033 16508 defer20 200K 199985 60 130 153 26 15737 14247 defer50 200K 199968 78 142 181 23 12113 11609 defer200 200K 199997 163 252 304 18 8449 9155 fullbusy 200K 199993 46 117 132 100 43959 23320 napibusy 200K 200006 100 237 275 56 25016 24866 suspend0 200K 200012 105 249 432 29 14369 11844 suspend10 200K 200004 53 123 141 32 19432 16752 suspend20 200K 200014 58 126 151 30 16356 14670 suspend50 200K 200018 73 134 176 26 13245 12416 suspend200 200K 200027 149 250 302 20 9508 9781 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 399984 139 268 715 40 9437 9299 defer10 400K 400002 59 133 165 53 14089 12908 defer20 400K 400016 66 140 171 47 12085 11682 defer50 400K 400037 87 161 198 39 9528 9879 defer200 400K 399954 181 273 329 32 7326 8438 fullbusy 400K 399951 50 123 155 100 21990 16097 napibusy 400K 399997 76 221 271 83 18260 16511 suspend0 400K 399991 125 337 768 48 11051 9629 suspend10 400K 399990 57 129 161 54 13629 12841 suspend20 400K 399922 61 135 167 49 12055 11715 suspend50 400K 400024 75 148 186 42 10049 10243 suspend200 400K 399936 154 267 325 34 7770 8677 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 600064 148 265 576 61 9276 8757 defer10 600K 599985 71 147 204 76 12048 10863 defer20 600K 600024 75 151 199 66 10572 10328 defer50 600K 600054 94 172 217 55 8584 9144 defer200 600K 600030 200 299 355 45 6874 8189 fullbusy 600K 599956 55 127 176 100 14650 13968 napibusy 600K 599956 64 163 252 96 14022 14153 suspend0 600K 600029 126 306 724 70 10393 8977 suspend10 600K 599997 63 137 194 70 10991 11005 suspend20 600K 600012 67 141 194 65 10108 10359 suspend50 600K 600045 80 157 203 57 8747 9320 suspend200 600K 599940 158 277 344 48 7221 8354 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800025 179 298 555 86 9572 8297 defer10 800K 799275 224 633 1271 96 10679 8904 defer20 800K 800041 114 226 328 90 10122 8917 defer50 800K 799936 118 207 288 77 8820 8607 defer200 800K 799994 228 341 403 65 7424 8130 fullbusy 800K 799964 62 136 192 100 10992 12518 napibusy 800K 799971 65 142 216 99 10911 12529 suspend0 800K 799965 126 250 533 86 9489 8496 suspend10 800K 799995 69 145 201 83 9475 9764 suspend20 800K 799931 74 151 209 79 8976 9336 suspend50 800K 799946 87 168 224 71 7993 8794 suspend200 800K 799993 160 292 357 62 6967 8184 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 915792 3498 5740 6239 97 9388 7930 defer10 1000K 876285 3896 6095 6418 99 9960 8542 defer20 1000K 914909 3107 5771 6283 97 9407 8284 defer50 1000K 928426 2977 5591 5931 97 9214 8012 defer200 1000K 959989 3097 5306 5929 96 8816 7908 fullbusy 1000K 1000102 74 155 213 100 8796 10559 napibusy 1000K 1000006 74 154 216 100 8787 10654 suspend0 1000K 960757 2223 5715 7029 98 8964 7993 suspend10 1000K 999926 80 162 222 92 8246 8922 suspend20 1000K 1000095 85 166 226 89 7966 8719 suspend50 1000K 1000067 96 180 238 84 7476 8419 suspend200 1000K 999968 163 298 363 76 6798 8061 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1054805 4152 5298 5743 100 8332 7890 defer10 MAX 937098 4598 6010 6347 100 9378 8407 defer20 MAX 988905 4389 5637 5990 100 8886 8106 defer50 MAX 1067194 3960 5216 5544 100 8235 7911 defer200 MAX 1054967 4084 5496 5821 100 8323 7871 fullbusy MAX 1248006 3472 3918 3979 100 7050 7919 napibusy MAX 1128384 3742 7958 10753 100 7776 7872 suspend0 MAX 1034456 4242 5668 6042 100 8497 7912 suspend10 MAX 1229229 3513 3926 3986 100 7156 7937 suspend20 MAX 1226845 3514 3939 3985 100 7171 7937 suspend50 MAX 1230757 3513 3935 3983 100 7140 7935 suspend200 MAX 1230424 3503 3934 3984 100 7142 7927 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2 can take control from Loop 1, if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2 and 3 "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2, which essentially tilts this in favour of Loop 3. If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3 cannot take control from Loop 1. Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. This is shown in the results above: compare suspend0 with the base case. Note that the lack of napi_defer_hard_irqs and gro_flush_timeout produce similar results for both, which encourages the use of napi_defer_hard_irqs and gro_flush_timeout in addition to irq_suspend_timeout. - Can the new timeout value be threaded through the new epoll ioctl ? Only with difficulty. The epoll ioctl sets options on an epoll context and the NAPI ID associated with an epoll context can change based on what file descriptors a user app adds to the epoll context. This would introduce complexity in the API from the user perspective and also complexity in the kernel. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the results. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v6: - Updated the cover letter with a full re-run of all test cases, including a new case suspend0, as requested by Sridhar previously. - Updated the kernel documentation in patch 7 as suggested by Bagas Sanjaya, which improved the htmldoc output. v5: https://lore.kernel.org/netdev/20241103052421.518856-1-jdamato@fastly.com/ - Adjusted patch 5 to only suspend IRQs when ep_send_events returns a positive return value. This issue was pointed out by Hillf Danton. - Updated the commit message of patch 6 which still mentioned netcat, despite the code being updated in v4 to replace it with socat and fixed misspelling of netdevsim. - Fixed a minor typo in patch 7 and removed an unnecessary paragraph. - Added Sridhar Samudrala's Reviewed-by to patch 1-5 and 7. v4: https://lore.kernel.org/netdev/20241102005214.32443-1-jdamato@fastly.com/ - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: https://lore.kernel.org/netdev/20241101004846.32532-1-jdamato@fastly.com/ - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (5): net: Add napi_struct parameter irq_suspend_timeout net: Suspend softirq when prefer_busy_poll is set net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 170 ++++++++- fs/eventpoll.c | 36 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 58 +++- net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 164 +++++++++ tools/testing/selftests/net/busy_poller.c | 328 ++++++++++++++++++ 15 files changed, 805 insertions(+), 11 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dbb9a7ef347828870df3e5e6ddf19469a3277fc9 -- 2.25.1

1 year, 1 month

2
3
0 0

[PATCH net-next v7 00/12] selftests: ncdevmem: Add ncdevmem to ksft

by Stanislav Fomichev

The goal of the series is to simplify and make it possible to use ncdevmem in an automated way from the ksft python wrapper. ncdevmem is slowly mutated into a state where it uses stdout to print the payload and the python wrapper is added to make sure the arrived payload matches the expected one. v7: - fix validation (Mina) - add support for working with non ::ffff-prefixed addresses (Mina) v6: - fix compilation issue in 'Unify error handling' patch (Jakub) v5: - properly handle errors from inet_pton() and socket() (Paolo) - remove unneeded import from python selftest (Paolo) v4: - keep usage example with validation (Mina) - fix compilation issue in one patch (s/start_queues/start_queue/) v3: - keep and refine the comment about ncdevmem invocation (Mina) - add the comment about not enforcing exit status for ntuple reset (Mina) - make configure_headersplit more robust (Mina) - use num_queues/2 in selftest and let the users override it (Mina) - remove memory_provider.memcpy_to_device (Mina) - keep ksft as is (don't use -v validate flags): we are gonna need a --debug-disable flag to make it less chatty; otherwise it times out when sending too much data; so leaving it as a separate follow up v2: - don't remove validation (Mina) - keep 5-tuple flow steering but use it only when -c is provided (Mina) - remove separate flag for probing (Mina) - move ncdevmem under drivers/net/hw, not drivers/net (Jakub) Cc: Mina Almasry <almasrymina(a)google.com> Stanislav Fomichev (12): selftests: ncdevmem: Redirect all non-payload output to stderr selftests: ncdevmem: Separate out dmabuf provider selftests: ncdevmem: Unify error handling selftests: ncdevmem: Make client_ip optional selftests: ncdevmem: Remove default arguments selftests: ncdevmem: Switch to AF_INET6 selftests: ncdevmem: Properly reset flow steering selftests: ncdevmem: Use YNL to enable TCP header split selftests: ncdevmem: Remove hard-coded queue numbers selftests: ncdevmem: Run selftest when none of the -s or -c has been provided selftests: ncdevmem: Move ncdevmem under drivers/net/hw selftests: ncdevmem: Add automated test .../selftests/drivers/net/hw/.gitignore | 1 + .../testing/selftests/drivers/net/hw/Makefile | 9 + .../selftests/drivers/net/hw/devmem.py | 45 + .../selftests/drivers/net/hw/ncdevmem.c | 786 ++++++++++++++++++ tools/testing/selftests/net/.gitignore | 1 - tools/testing/selftests/net/Makefile | 8 - tools/testing/selftests/net/ncdevmem.c | 570 ------------- 7 files changed, 841 insertions(+), 579 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/.gitignore create mode 100755 tools/testing/selftests/drivers/net/hw/devmem.py create mode 100644 tools/testing/selftests/drivers/net/hw/ncdevmem.c delete mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.47.0

1 year, 1 month

4
30
0 0

[PATCH v3 0/4] Add support for the Bus Lock Threshold

by Manali Shukla

Misbehaving guests can cause bus locks to degrade the performance of a system. Non-WB (write-back) and misaligned locked RMW (read-modify-write) instructions are referred to as "bus locks" and require system wide synchronization among all processors to guarantee the atomicity. The bus locks can impose notable performance penalties for all processors within the system. Support for the Bus Lock Threshold is indicated by CPUID Fn8000_000A_EDX[29] BusLockThreshold=1, the VMCB provides a Bus Lock Threshold enable bit and an unsigned 16-bit Bus Lock Threshold count. VMCB intercept bit VMCB Offset Bits Function 14h 5 Intercept bus lock operations Bus lock threshold count VMCB Offset Bits Function 120h 15:0 Bus lock counter During VMRUN, the bus lock threshold count is fetched and stored in an internal count register. Prior to executing a bus lock within the guest, the processor verifies the count in the bus lock register. If the count is greater than zero, the processor executes the bus lock, reducing the count. However, if the count is zero, the bus lock operation is not performed, and instead, a Bus Lock Threshold #VMEXIT is triggered to transfer control to the Virtual Machine Monitor (VMM). A Bus Lock Threshold #VMEXIT is reported to the VMM with VMEXIT code 0xA5h, VMEXIT_BUSLOCK. EXITINFO1 and EXITINFO2 are set to 0 on a VMEXIT_BUSLOCK. On a #VMEXIT, the processor writes the current value of the Bus Lock Threshold Counter to the VMCB. More details about the Bus Lock Threshold feature can be found in AMD APM [1]. v2 -> v3 - Drop parch to add virt tag in /proc/cpuinfo. - Incorporated Tom's review comments. v1 -> v2 - Incorporated misc review comments from Sean. - Removed bus_lock_counter module parameter. - Set the value of bus_lock_counter to zero by default and reload the value by 1 in bus lock exit handler. - Add documentation for the behavioral difference for KVM_EXIT_BUS_LOCK. - Improved selftest for buslock to work on SVM and VMX. - Rewrite the commit messages. Patches are prepared on kvm-next/next (efbc6bd090f4). Testing done: - Added a selftest for the Bus Lock Threshold functionality. - The bus lock threshold selftest has been tested on both Intel and AMD platforms. - Tested the Bus Lock Threshold functionality on SEV, SEV-ES, SEV-SNP guests. - Tested the Bus Lock Threshold functionality on nested guests. v1: https://lore.kernel.org/kvm/20240709175145.9986-4-manali.shukla@amd.com/T/ v2: https://lore.kernel.org/kvm/20241001063413.687787-4-manali.shukla@amd.com/T/ [1]: AMD64 Architecture Programmer's Manual Pub. 24593, April 2024, Vol 2, 15.14.5 Bus Lock Threshold. https://bugzilla.kernel.org/attachment.cgi?id=306250 Manali Shukla (2): x86/cpufeatures: Add CPUID feature bit for the Bus Lock Threshold KVM: X86: Add documentation about behavioral difference for KVM_EXIT_BUS_LOCK Nikunj A Dadhania (2): KVM: SVM: Enable Bus lock threshold exit KVM: selftests: Add bus lock exit test Documentation/virt/kvm/api.rst | 4 + arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/svm.h | 5 +- arch/x86/include/uapi/asm/svm.h | 2 + arch/x86/kvm/svm/nested.c | 10 ++ arch/x86/kvm/svm/svm.c | 27 ++++ tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/x86_64/kvm_buslock_test.c | 130 ++++++++++++++++++ 8 files changed, 179 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/kvm/x86_64/kvm_buslock_test.c base-commit: efbc6bd090f48ccf64f7a8dd5daea775821d57ec -- 2.34.1

1 year, 1 month

4
13
0 0

Testing Quality Call notes - 2024-10-31

by Laura Nao

Hello, KernelCI is hosting a bi-weekly call on Thursday to discuss improvements to existing upstream tests, the development of new tests to increase kernel testing coverage, and the enablement of these tests in KernelCI. In recent months, we at Collabora have focused on various kernel areas, assessing the tests already available upstream and contributing patches to make them easily runnable in CIs. Below is a list of the tests we've been working on and their latest status updates, as discussed in the last meeting held on 2024-10-31: *Boot time test* - Sent v2: https://lore.kernel.org/all/20241018101439.20849-1-laura.nao@collabora.com/ - Changes in v2 driven by feedback received in the LPC session *ACPI probe kselftest* - RFCv2: https://lore.kernel.org/all/20240308144933.337107-1-laura.nao@collabora.com/ - Related upstream discussion on probe status tracking through printks: https://lore.kernel.org/lkml/dc7af563-530d-4e1f-bcbb-90bcfc2fe11a@stanley.m… Please reply to this thread if you'd like to join the call or discuss any of the topics further. We look forward to collaborating with the community to improve upstream tests and expand coverage to more areas of interest within the kernel. Best regards, Laura Nao

1 year, 1 month

1
0
0 0

[PATCH net-next v2 0/4] Introduce VLAN support in HSR

by MD Danish Anwar

This series adds VLAN support to HSR framework. This series also adds VLAN support to HSR mode of ICSSG Ethernet driver. Changes from v1 to v2: *) Added patch 4/4 to add test script related to VLAN in HSR as asked by Lukasz Majewski <lukma(a)denx.de> v1 https://lore.kernel.org/all/20241004074715.791191-1-danishanwar@ti.com/ MD Danish Anwar (1): selftests: hsr: Add test for VLAN Murali Karicheri (1): net: hsr: Add VLAN CTAG filter support Ravi Gunasekaran (1): net: ti: icssg-prueth: Add VLAN support for HSR mode WingMan Kwok (1): net: hsr: Add VLAN support drivers/net/ethernet/ti/icssg/icssg_prueth.c | 45 +++++++++++- net/hsr/hsr_device.c | 76 ++++++++++++++++++-- net/hsr/hsr_forward.c | 19 +++-- tools/testing/selftests/net/hsr/config | 1 + tools/testing/selftests/net/hsr/hsr_ping.sh | 63 +++++++++++++++- 5 files changed, 191 insertions(+), 13 deletions(-) base-commit: 1bf70e6c3a5346966c25e0a1ff492945b25d3f80 -- 2.34.1

1 year, 1 month

4
10
0 0

[PATCH net v6] ipv6: Fix soft lockups in fib6_select_path under high next hop churn

by Omid Ehtemam-Haghighi

Soft lockups have been observed on a cluster of Linux-based edge routers located in a highly dynamic environment. Using the `bird` service, these routers continuously update BGP-advertised routes due to frequently changing nexthop destinations, while also managing significant IPv6 traffic. The lockups occur during the traversal of the multipath circular linked-list in the `fib6_select_path` function, particularly while iterating through the siblings in the list. The issue typically arises when the nodes of the linked list are unexpectedly deleted concurrently on a different core—indicated by their 'next' and 'previous' elements pointing back to the node itself and their reference count dropping to zero. This results in an infinite loop, leading to a soft lockup that triggers a system panic via the watchdog timer. Apply RCU primitives in the problematic code sections to resolve the issue. Where necessary, update the references to fib6_siblings to annotate or use the RCU APIs. Include a test script that reproduces the issue. The script periodically updates the routing table while generating a heavy load of outgoing IPv6 traffic through multiple iperf3 clients. It consistently induces infinite soft lockups within a couple of minutes. Kernel log: 0 [ffffbd13003e8d30] machine_kexec at ffffffff8ceaf3eb 1 [ffffbd13003e8d90] __crash_kexec at ffffffff8d0120e3 2 [ffffbd13003e8e58] panic at ffffffff8cef65d4 3 [ffffbd13003e8ed8] watchdog_timer_fn at ffffffff8d05cb03 4 [ffffbd13003e8f08] __hrtimer_run_queues at ffffffff8cfec62f 5 [ffffbd13003e8f70] hrtimer_interrupt at ffffffff8cfed756 6 [ffffbd13003e8fd0] __sysvec_apic_timer_interrupt at ffffffff8cea01af 7 [ffffbd13003e8ff0] sysvec_apic_timer_interrupt at ffffffff8df1b83d -- <IRQ stack> -- 8 [ffffbd13003d3708] asm_sysvec_apic_timer_interrupt at ffffffff8e000ecb [exception RIP: fib6_select_path+299] RIP: ffffffff8ddafe7b RSP: ffffbd13003d37b8 RFLAGS: 00000287 RAX: ffff975850b43600 RBX: ffff975850b40200 RCX: 0000000000000000 RDX: 000000003fffffff RSI: 0000000051d383e4 RDI: ffff975850b43618 RBP: ffffbd13003d3800 R8: 0000000000000000 R9: ffff975850b40200 R10: 0000000000000000 R11: 0000000000000000 R12: ffffbd13003d3830 R13: ffff975850b436a8 R14: ffff975850b43600 R15: 0000000000000007 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 9 [ffffbd13003d3808] ip6_pol_route at ffffffff8ddb030c 10 [ffffbd13003d3888] ip6_pol_route_input at ffffffff8ddb068c 11 [ffffbd13003d3898] fib6_rule_lookup at ffffffff8ddf02b5 12 [ffffbd13003d3928] ip6_route_input at ffffffff8ddb0f47 13 [ffffbd13003d3a18] ip6_rcv_finish_core.constprop.0 at ffffffff8dd950d0 14 [ffffbd13003d3a30] ip6_list_rcv_finish.constprop.0 at ffffffff8dd96274 15 [ffffbd13003d3a98] ip6_sublist_rcv at ffffffff8dd96474 16 [ffffbd13003d3af8] ipv6_list_rcv at ffffffff8dd96615 17 [ffffbd13003d3b60] __netif_receive_skb_list_core at ffffffff8dc16fec 18 [ffffbd13003d3be0] netif_receive_skb_list_internal at ffffffff8dc176b3 19 [ffffbd13003d3c50] napi_gro_receive at ffffffff8dc565b9 20 [ffffbd13003d3c80] ice_receive_skb at ffffffffc087e4f5 [ice] 21 [ffffbd13003d3c90] ice_clean_rx_irq at ffffffffc0881b80 [ice] 22 [ffffbd13003d3d20] ice_napi_poll at ffffffffc088232f [ice] 23 [ffffbd13003d3d80] __napi_poll at ffffffff8dc18000 24 [ffffbd13003d3db8] net_rx_action at ffffffff8dc18581 25 [ffffbd13003d3e40] __do_softirq at ffffffff8df352e9 26 [ffffbd13003d3eb0] run_ksoftirqd at ffffffff8ceffe47 27 [ffffbd13003d3ec0] smpboot_thread_fn at ffffffff8cf36a30 28 [ffffbd13003d3ee8] kthread at ffffffff8cf2b39f 29 [ffffbd13003d3f28] ret_from_fork at ffffffff8ce5fa64 30 [ffffbd13003d3f50] ret_from_fork_asm at ffffffff8ce03cbb Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Adrian Oliver <kernel(a)aoliver.ca> Signed-off-by: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi(a)menlosecurity.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: David Ahern <dsahern(a)gmail.com> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Ido Schimmel <idosch(a)idosch.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Simon Horman <horms(a)kernel.org> Cc: netdev(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- v5 -> v6: * Adjust the comment line lengths in the test script to a maximum of 80 characters * Change memory allocation in inet6_rt_notify from gfp_any() to GFP_ATOMIC for atomic allocation in non-blocking contexts, as suggested by Ido Schimmel * NOTE: I have executed the test script on both bare-metal servers and virtualized environments such as QEMU and vng. In the case of bare-metal, it consistently triggers a soft lockup in under a minute on unpatched kernels. For the virtualized environments, an unpatched kernel compiled with the Ubuntu 24.04 configuration also triggers a soft lockup, though it takes longer; however, it did not trigger a soft lockup on kernels compiled with configurations provided in: https://github.com/linux-netdev/nipa/wiki/How-to-run-netdev-selftests-CI-st… leading to potential false negatives in the test results. I am curious if this test can be executed on a bare-metal machine within a CI system, if such a setup exists, rather than in a virtualized environment. If that’s not possible, how can I apply a different kernel configuration, such as the one used in Ubuntu 24.04, for this test? Please advise. v4 -> v5: * Addressed review comments from Paolo Abeni. * Added additional clarifying comments in the test script. * Minor cleanup performed in the test script. v3 -> v4: * Added RCU primitives to rt6_fill_node(). I found that this function is typically called either with a table lock held or within rcu_read_lock/rcu_read_unlock pairs, except in the following call chain, where the protection is unclear: rt_fill_node() fib6_info_hw_flags_set() mlxsw_sp_fib6_offload_failed_flag_set() mlxsw_sp_router_fib6_event_work() The last function is initialized as a work item in mlxsw_sp_router_fib_event() and scheduled for deferred execution. I am unsure if the execution context of this work item is protected by any table lock or rcu_read_lock/rcu_read_unlock pair, so I have added the protection. Please let me know if this is redundant. * Other review comments addressed v2 -> v3: * Removed redundant rcu_read_lock()/rcu_read_unlock() pairs * Revised the test script based on Ido Schimmel's feedback * Updated the test script to ensure compatibility with the latest iperf3 version * Fixed new warnings generated with 'C=2' in the previous version * Other review comments addressed v1 -> v2: * list_del_rcu() is applied exclusively to legacy multipath code * All occurrences of fib6_siblings have been modified to utilize RCU APIs for annotation and usage. * Additionally, a test script for reproducing the reported issue is included --- net/ipv6/ip6_fib.c | 8 +- net/ipv6/route.c | 45 ++- tools/testing/selftests/net/Makefile | 1 + .../net/ipv6_route_update_soft_lockup.sh | 262 ++++++++++++++++++ 4 files changed, 297 insertions(+), 19 deletions(-) create mode 100755 tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index eb111d20615c..9a1c59275a10 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1190,8 +1190,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->fib6_siblings, - &sibling->fib6_siblings); + list_add_tail_rcu(&rt->fib6_siblings, + &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, @@ -1252,7 +1252,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } @@ -1970,7 +1970,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b4251915585f..b9b986bda943 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -413,8 +413,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; + struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -440,8 +440,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; - list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, - fib6_siblings) { + list_for_each_entry_rcu(sibling, &match->fib6_siblings, + fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; @@ -5195,14 +5195,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ + rcu_read_lock(); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { - rt = list_first_entry(&rt_last->fib6_siblings, - struct fib6_info, - fib6_siblings); + rt = list_first_or_null_rcu(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); + + rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) @@ -5547,17 +5551,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { - struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; + struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } + + rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } @@ -5721,7 +5729,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); @@ -5733,14 +5741,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, 0) < 0) goto nla_put_failure; - list_for_each_entry_safe(sibling, next_sibling, - &rt->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &rt->fib6_siblings, + fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6, 0) < 0) + AF_INET6, 0) < 0) { + rcu_read_unlock(); + goto nla_put_failure; + } } + rcu_read_unlock(); + nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) @@ -6177,7 +6192,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; @@ -6190,7 +6205,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, - info->nlh, gfp_any()); + info->nlh, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 649f1fe0dc46..88cbac27aa10 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -96,6 +96,7 @@ TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py +TEST_PROGS += ipv6_route_update_soft_lockup.sh # YNL files, must be before "include ..lib.mk" EXTRA_CLEAN += $(OUTPUT)/libynl.a diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh new file mode 100755 index 000000000000..c61a7a8352cf --- /dev/null +++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh @@ -0,0 +1,262 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Testing for potential kernel soft lockup during IPv6 routing table +# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup +# occurs, a kernel panic will be triggered to prevent associated issues. +# +# +# Test Environment Layout +# +# ┌----------------┐ ┌----------------┐ +# | SOURCE_NS | | SINK_NS | +# | NAMESPACE | | NAMESPACE | +# |(iperf3 clients)| |(iperf3 servers)| +# | | | | +# | | | | +# | ┌-----------| nexthops |---------┐ | +# | |veth_source|<--------------------------------------->|veth_sink|<┐ | +# | └-----------|2001:0DB8:1::0:1/96 2001:0DB8:1::1:1/96 |---------┘ | | +# | | ^ 2001:0DB8:1::1:2/96 | | | +# | | . . | fwd | | +# | ┌---------┐ | . . | | | +# | | IPv6 | | . . | V | +# | | routing | | . 2001:0DB8:1::1:80/96| ┌-----┐ | +# | | table | | . | | lo | | +# | | nexthop | | . └--------┴-----┴-┘ +# | | update | | ............................> 2001:0DB8:2::1:1/128 +# | └-------- ┘ | +# └----------------┘ +# +# The test script sets up two network namespaces, source_ns and sink_ns, +# connected via a veth link. Within source_ns, it continuously updates the +# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop +# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a +# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds. +# +# Simultaneously, multiple iperf3 clients within source_ns generate heavy +# outgoing IPv6 traffic. Each client is assigned a unique port number starting +# at 5000 and incrementing sequentially. Each client targets a unique iperf3 +# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface +# using the same port number. +# +# The number of iperf3 servers and clients is set to half of the total +# available cores on each machine. +# +# NOTE: We have tested this script on machines with various CPU specifications, +# ranging from lower to higher performance as listed below. The test script +# effectively triggered a kernel soft lockup on machines running an unpatched +# kernel in under a minute: +# +# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz +# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz +# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz +# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz +# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz +# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz +# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz +# +# On less performant machines, you may need to increase the TEST_DURATION +# parameter to enhance the likelihood of encountering a race condition leading +# to a kernel soft lockup and avoid a false negative result. +# +# NOTE: The test may not produce the expected result in virtualized +# environments (e.g., qemu) due to differences in timing and CPU handling, +# which can affect the conditions needed to trigger a soft lockup. + +source lib.sh +source net_helper.sh + +TEST_DURATION=300 +ROUTING_TABLE_REFRESH_PERIOD=0.01 + +IPERF3_BITRATE="300m" + + +IPV6_NEXTHOP_ADDR_COUNT="128" +IPV6_NEXTHOP_ADDR_MASK="96" +IPV6_NEXTHOP_PREFIX="2001:0DB8:1" + + +SOURCE_TEST_IFACE="veth_source" +SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96" + +SINK_TEST_IFACE="veth_sink" +# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses: +# 2001:0DB8:1::1:1 to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT} +SINK_LOOPBACK_IFACE="lo" +SINK_LOOPBACK_IP_MASK="128" +SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1" + +nexthop_ip_list="" +termination_signal="" +kernel_softlokup_panic_prev_val="" + +terminate_ns_processes_by_pattern() { + local ns=$1 + local pattern=$2 + + for pid in $(ip netns pids ${ns}); do + [ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid + done +} + +cleanup() { + echo "info: cleaning up namespaces and terminating all processes within them..." + + + # Terminate iperf3 instances running in the source_ns. To avoid race + # conditions, first iterate over the PIDs and terminate those + # associated with the bash shells running the + # `while true; do iperf3 -c ...; done` loops. In a second iteration, + # terminate the individual `iperf3 -c ...` instances. + terminate_ns_processes_by_pattern ${source_ns} while + terminate_ns_processes_by_pattern ${source_ns} iperf3 + + # Repeat the same process for sink_ns + terminate_ns_processes_by_pattern ${sink_ns} while + terminate_ns_processes_by_pattern ${sink_ns} iperf3 + + # Check if any iperf3 instances are still running. This could happen + # if a core has entered an infinite loop and the timeout for detecting + # the soft lockup has not expired, but either the test interval has + # already elapsed or the test was terminated manually (e.g., with ^C) + for pid in $(ip netns pids ${source_ns}); do + if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then + echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!" + exit ${ksft_fail} + fi + done + + if [ "$termination_signal" == "SIGINT" ]; then + echo "SKIP: Termination due to ^C (SIGINT)" + elif [ "$termination_signal" == "SIGALRM" ]; then + echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test" + fi + + cleanup_ns ${source_ns} ${sink_ns} + + sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val} +} + +setup_prepare() { + setup_ns source_ns sink_ns + + ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns} + + # Setting up the Source namespace + ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE} + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000 + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up + ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1 + + # Setting up the Sink namespace + ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE} + ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1 + + ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1 + + + # Populate nexthop IPv6 addresses on the test interface in the sink_ns + echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..." + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE}; + done + + # Preparing list of nexthops + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1" + done +} + + +test_soft_lockup_during_routing_table_refresh() { + # Start num_of_iperf_servers iperf3 servers in the sink_ns namespace, + # each listening on ports starting at 5001 and incrementing + # sequentially. Since iperf3 instances may terminate unexpectedly, a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null" + ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + # Wait for the iperf3 servers to be ready + for i in $(seq ${num_of_iperf_servers}); do + port=$(printf '5%03d' ${i}); + wait_local_port_listen ${sink_ns} ${port} tcp + done + + # Continuously refresh the routing table in the background within + # the source_ns namespace + ip netns exec ${source_ns} bash -c " + while \$(ip netns list | grep -q ${source_ns}); do + ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list}; + sleep ${ROUTING_TABLE_REFRESH_PERIOD}; + ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK}; + done &" + + # Start num_of_iperf_servers iperf3 clients in the source_ns namespace, + # each sending TCP traffic on sequential ports starting at 5001. + # Since iperf3 instances may terminate unexpectedly (e.g., if the route + # to the server is deleted in the background during a route refresh), a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null" + ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..." + echo "info: A kernel soft lockup, if detected, results in a kernel panic!" + + wait +} + +# Make sure 'iperf3' is installed, skip the test otherwise +if [ ! -x "$(command -v "iperf3")" ]; then + echo "SKIP: 'iperf3' is not installed. Skipping the test." + exit ${ksft_skip} +fi + +# Determine the number of cores on the machine +num_of_iperf_servers=$(( $(nproc)/2 )) + +# Check if we are running on a multi-core machine, skip the test otherwise +if [ "${num_of_iperf_servers}" -eq 0 ]; then + echo "SKIP: This test is not valid on a single core machine!" + exit ${ksft_skip} +fi + +# Since the kernel soft lockup we're testing causes at least one core to enter +# an infinite loop, destabilizing the host and likely affecting subsequent +# tests, we trigger a kernel panic instead of reporting a failure and +# continuing +kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic) +sysctl -qw kernel.softlockup_panic=1 + +handle_sigint() { + termination_signal="SIGINT" + cleanup + exit ${ksft_skip} +} + +handle_sigalrm() { + termination_signal="SIGALRM" + cleanup + exit ${ksft_pass} +} + +trap handle_sigint SIGINT +trap handle_sigalrm SIGALRM + +(sleep ${TEST_DURATION} && kill -s SIGALRM $$)& + +setup_prepare +test_soft_lockup_during_routing_table_refresh -- 2.43.0

1 year, 1 month

3
3
0 0

[PATCH v4] selftests: clone3: Use the capget and capset syscall directly

by zhouyuhang

From: zhouyuhang <zhouyuhang(a)kylinos.cn> The libcap commit aca076443591 ("Make cap_t operations thread safe.") added a __u8 mutex at the beginning of the struct _cap_struct, it changes the offset of the members in the structure that breaks the assumption made in the "struct libcap" definition in clone3_cap_checkpoint_restore.c. This causes the call to cap_set_proc here to fail with error code EPERM, and the output is as follows: # RUN global.clone3_cap_checkpoint_restore ... # clone3() syscall supported # clone3_cap_checkpoint_restore.c:151:clone3_cap_checkpoint_restore:Child has PID 130508 cap_set_proc: Operation not permitted # clone3_cap_checkpoint_restore.c:160:clone3_cap_checkpoint_restore:Expected set_capability() (-1) == 0 (0) # clone3_cap_checkpoint_restore.c:161:clone3_cap_checkpoint_restore:Could not set CAP_CHECKPOINT_RESTORE # clone3_cap_checkpoint_restore: Test terminated by assertion # FAIL global.clone3_cap_checkpoint_restore Changing to using capget and capset syscall directly here can fix this error, just like what the commit 663af70aabb7 ("bpf: selftests: Add helpers to directly use the capget and capset syscall") does. The output is as follows: # RUN global.clone3_cap_checkpoint_restore ... # clone3() syscall supported # clone3_cap_checkpoint_restore.c:160:clone3_cap_checkpoint_restore:Child has PID 23708 # clone3_cap_checkpoint_restore.c:91:clone3_cap_checkpoint_restore:[23707] Trying clone3() with CLONE_SET_TID to 23708 # clone3_cap_checkpoint_restore.c:58:clone3_cap_checkpoint_restore:Operation not permitted - Failed to create new process # clone3_cap_checkpoint_restore.c:93:clone3_cap_checkpoint_restore:[23707] clone3() with CLONE_SET_TID 23708 says:-1 # clone3_cap_checkpoint_restore.c:91:clone3_cap_checkpoint_restore:[23707] Trying clone3() with CLONE_SET_TID to 23708 # clone3_cap_checkpoint_restore.c:73:clone3_cap_checkpoint_restore:I am the parent (23707). My child's pid is 23708 # clone3_cap_checkpoint_restore.c:66:clone3_cap_checkpoint_restore:I am the child, my PID is 23708 (expected 23708) # clone3_cap_checkpoint_restore.c:93:clone3_cap_checkpoint_restore:[23707] clone3() with CLONE_SET_TID 23708 says:0 # OK global.clone3_cap_checkpoint_restore ok 1 global.clone3_cap_checkpoint_restore # PASSED: 1 / 1 tests passed. Signed-off-by: zhouyuhang <zhouyuhang(a)kylinos.cn> --- v4: * Add some comments and modify the output and return value when set_capability fails v3: * Remove locally declared system calls and retained the - lcap in the Makefile. v2: * Move locally declared system calls to header file. v1: * Directly using capget and capset and declare them locally. --- .../clone3/clone3_cap_checkpoint_restore.c | 77 +++++++++++-------- 1 file changed, 43 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 3c196fa86c99..076f9d4cce60 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -27,6 +27,13 @@ #include "../kselftest_harness.h" #include "clone3_selftests.h" +/* + * Prevent not being defined in the header file + */ +#ifndef CAP_CHECKPOINT_RESTORE +#define CAP_CHECKPOINT_RESTORE 40 +#endif + static void child_exit(int ret) { fflush(stdout); @@ -87,47 +94,49 @@ static int test_clone3_set_tid(struct __test_metadata *_metadata, return ret; } -struct libcap { - struct __user_cap_header_struct hdr; +static int set_capability(struct __test_metadata *_metadata) +{ struct __user_cap_data_struct data[2]; -}; -static int set_capability(void) -{ - cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID }; - struct libcap *cap; - int ret = -1; - cap_t caps; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); - return -1; - } + /* + * Only _LINUX_CAPABILITY_VERSION_3 can be used here. + * _LINUX_CAPABILITY_VERSION_1 represents use 32-bit capabilities, + * using it will cause CAP_CHECKPOINT_RESTORE to not be set. + * _LINUX_CAPABILITY_VERSION_2 has already been deprecated. + */ + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; - /* Drop all capabilities */ - if (cap_clear(caps)) { - perror("cap_clear"); - goto out; + /* + * CAP_CHECKPOINT_RESTORE is greater than 31, so we need two u32. + * cap0 is the lower 32bit and cap1 is the higher 32bit, they will + * be combined into a u64 in mk_kernel_cap. + */ + __u32 cap0 = 1 << CAP_SETUID | 1 << CAP_SETGID; + __u32 cap1 = 1 << (CAP_CHECKPOINT_RESTORE - 32); + int ret; + + ret = capget(&hdr, data); + if (ret) { + TH_LOG("%s - Failed to get capability", strerror(errno)); + return -errno; } - cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET); - cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET); + /* Drop all capabilities */ + memset(&data, 0, sizeof(data)); - cap = (struct libcap *) caps; + data[0].effective |= cap0; + data[0].permitted |= cap0; - /* 40 -> CAP_CHECKPOINT_RESTORE */ - cap->data[1].effective |= 1 << (40 - 32); - cap->data[1].permitted |= 1 << (40 - 32); + data[1].effective |= cap1; + data[1].permitted |= cap1; - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; + ret = capset(&hdr, data); + if (ret) { + TH_LOG("%s - Failed to set capability", strerror(errno)); + return -errno; } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); return ret; } @@ -157,7 +166,7 @@ TEST(clone3_cap_checkpoint_restore) /* After the child has finished, its PID should be free. */ set_tid[0] = pid; - ASSERT_EQ(set_capability(), 0) + ASSERT_EQ(set_capability(_metadata), 0) TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); ASSERT_EQ(prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0), 0); @@ -169,7 +178,7 @@ TEST(clone3_cap_checkpoint_restore) set_tid[0] = pid; /* This would fail without CAP_CHECKPOINT_RESTORE */ ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), -EPERM); - ASSERT_EQ(set_capability(), 0) + ASSERT_EQ(set_capability(_metadata), 0) TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); /* This should work as we have CAP_CHECKPOINT_RESTORE as non-root */ ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), 0); -- 2.27.0

1 year, 1 month

1
0
0 0

[PATCH] KVM: selftests: memslot_perf_test: increase guest sync timeout

by Maxim Levitsky

When memslot_perf_test is run nested, first iteration of test_memslot_rw_loop testcase, sometimes takes more than 2 seconds due to build of shadow page tables. Following iterations are fast. To be on the safe side, bump the timeout to 10 seconds. Signed-off-by: Maxim Levitsky <mlevitsk(a)redhat.com> --- tools/testing/selftests/kvm/memslot_perf_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 893366982f77b..e9189cbed4bb6 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -415,7 +415,7 @@ static bool _guest_should_exit(void) */ static noinline void host_perform_sync(struct sync_area *sync) { - alarm(2); + alarm(10); atomic_store_explicit(&sync->sync_flag, true, memory_order_release); while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) -- 2.26.3

1 year, 1 month

3
3
0 0

[PATCH] kvm: selftest: fix noop test in guest_memfd_test.c

by Patrick Roy

The loop in test_create_guest_memfd_invalid that is supposed to test that nothing is accepted as a valid flag to KVM_CREATE_GUEST_MEMFD was initializing `flag` as 0 instead of BIT(0). This caused the loop to immediately exit instead of iterating over BIT(0), BIT(1), ... . Fixes: 8a89efd43423 ("KVM: selftests: Add basic selftest for guest_memfd()") Signed-off-by: Patrick Roy <roypat(a)amazon.co.uk> --- tools/testing/selftests/kvm/guest_memfd_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index ba0c8e9960358..ce687f8d248fc 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -134,7 +134,7 @@ static void test_create_guest_memfd_invalid(struct kvm_vm *vm) size); } - for (flag = 0; flag; flag <<= 1) { + for (flag = BIT(0); flag; flag <<= 1) { fd = __vm_create_guest_memfd(vm, page_size, flag); TEST_ASSERT(fd == -1 && errno == EINVAL, "guest_memfd() with flag '0x%lx' should fail with EINVAL", -- 2.47.0

1 year, 1 month

4
4
0 0

[PATCH v3 0/9] SEV Kernel Selftests

by Pratik R. Sampat

This series primarily introduces SEV-SNP test for the kernel selftest framework. It tests boot, ioctl, pre fault, and fallocate in various combinations to exercise both positive and negative launch flow paths. Patch 1 - Adds a wrapper for the ioctl calls that decouple ioctl and asserts, which enables the use of negative test cases. No functional change intended. Patch 2 - Extend the sev smoke tests to use the SNP specific ioctl calls and sets up memory to boot a SNP guest VM Patch 3 - Adds SNP to shutdown testing Patch 4, 5 - Tests the ioctl path for SEV, SEV-ES and SNP Patch 6 - Adds support for SNP in KVM_SEV_INIT2 tests Patch 7,8,9 - Enable Prefault tests for SEV, SEV-ES and SNP The patchset is rebased on top of kvm-x86/next branch. v3: 1. Remove the assignments for the prefault and fallocate test type enums. 2. Fix error message for sev launch measure and finish. 3. Collect tested-by tags [Peter, Srikanth] v2: https://lore.kernel.org/kvm/20240816192310.117456-1-pratikrajesh.sampat@amd… 1. Add SMT parsing check to populate SNP policy flags 2. Extend Peter Gonda's shutdown test to include SNP 3. Introduce new tests for prefault which include exercising prefault, fallocate, hole-punch in various combinations. 4. Decouple ioctl patch reworked to introduce private variants of the the functions that call into the ioctl. Also reordered the patch for it to arrive first so that new APIs are not written right after their introduction. 5. General cleanups - adding comments, avoiding local booleans, better error message. Suggestions incorporated from Peter, Tom, and Sean. RFC: https://lore.kernel.org/kvm/20240710220540.188239-1-pratikrajesh.sampat@amd… Any feedback/review is highly appreciated! Michael Roth (2): KVM: selftests: Add interface to manually flag protected/encrypted ranges KVM: selftests: Add a CoCo-specific test for KVM_PRE_FAULT_MEMORY Pratik R. Sampat (7): KVM: selftests: Decouple SEV ioctls from asserts KVM: selftests: Add a basic SNP smoke test KVM: selftests: Add SNP to shutdown testing KVM: selftests: SEV IOCTL test KVM: selftests: SNP IOCTL test KVM: selftests: SEV-SNP test for KVM_SEV_INIT2 KVM: selftests: Interleave fallocate for KVM_PRE_FAULT_MEMORY tools/testing/selftests/kvm/Makefile | 1 + .../testing/selftests/kvm/include/kvm_util.h | 13 + .../selftests/kvm/include/x86_64/processor.h | 1 + .../selftests/kvm/include/x86_64/sev.h | 76 +++- tools/testing/selftests/kvm/lib/kvm_util.c | 53 ++- .../selftests/kvm/lib/x86_64/processor.c | 6 +- tools/testing/selftests/kvm/lib/x86_64/sev.c | 190 +++++++- .../kvm/x86_64/coco_pre_fault_memory_test.c | 421 ++++++++++++++++++ .../selftests/kvm/x86_64/sev_init2_tests.c | 13 + .../selftests/kvm/x86_64/sev_smoke_test.c | 297 +++++++++++- 10 files changed, 1023 insertions(+), 48 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/coco_pre_fault_memory_test.c -- 2.34.1

1 year, 1 month

2
27
0 0

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74)

by kernelci.org bot

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.12-rc3-23-ga4… Test: kselftest-lib Tree: kselftest Branch: next Describe: v6.12-rc3-23-ga44c26d7fa74 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/672978b37de8409f75c8685a Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lib.login: https://kernelci.org/test/case/id/672978b37de8409f75c8685b failing since 97 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 1 month

1
0
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.12-rc3-23-ga4… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.12-rc3-23-ga44c26d7fa74 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/67297a56d7f1f585c1c86864 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/67297a57d7f1f585c1c86865 failing since 97 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 1 month

1
0
0 0

kselftest/next kselftest-seccomp: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74)

by kernelci.org bot

kselftest/next kselftest-seccomp: 1 runs, 1 regressions (v6.12-rc3-23-ga44c26d7fa74) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.12-rc3-23-ga4… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.12-rc3-23-ga44c26d7fa74 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/67297bfb8d4223d56ec86863 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-23-ga44c26d7fa74/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/67297bfb8d4223d56ec86864 failing since 97 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 1 month

1
0
0 0

kselftest/next build: 6 builds: 2 failed, 4 passed, 1 warning (v6.12-rc3-23-ga44c26d7fa74)

by kernelci.org bot

kselftest/next build: 6 builds: 2 failed, 4 passed, 1 warning (v6.12-rc3-23-ga44c26d7fa74) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.12-rc3-23-ga44c2… Tree: kselftest Branch: next Git Describe: v6.12-rc3-23-ga44c26d7fa74 Git Commit: a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14fd19 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x14fd19 --- For more info write to <info(a)kernelci.org>

1 year, 1 month

1
0
0 0

[PATCH V4 00/15] selftests/resctrl: Support diverse platforms with MBM and MBA tests

by Reinette Chatre

Changes since V3: - V3: https://lore.kernel.org/all/cover.1729218182.git.reinette.chatre@intel.com/ - Rebased on HEAD 2a027d6bb660 of kselftest/next. - Fix empty string parsing issues pointed out by Ilpo. - Add Reviewed-by tags. - Please see individual patches for detailed changes. Changes since V2: - V2: https://lore.kernel.org/all/cover.1726164080.git.reinette.chatre@intel.com/ - Add fix to protect against buffer overflow when parsing text from sysfs files. - Add cleanup patch to address use of magic constants as pointed out by Ilpo. - Add Reviewed-by tags where received, except for "selftests/resctrl: Use cache size to determine "fill_buf" buffer size" that changed too much since receiving the Reviewed-by tag. - Please see individual patches for detailed changes. Changes since V1: - V1: https://lore.kernel.org/cover.1724970211.git.reinette.chatre@intel.com/ - V2 contains the same general solutions to stated problem as V1 but these are now preceded by more fixes (patches 1 to 5) and improved robustness (patches 6 to 9) to existing tests before the series gets back to solving the original problem with more confidence in patches 10 to 13. - The posibility of making "memflush = false" for CMT test was discussed during V1. Modifying this setting does not have a significant impact on the observed results that are already well within acceptable range and this version thus keeps original default. If performance was a goal it may be possible to do further experimentation where "memflush = false" could eliminate the need for the sleep(1) within the test wrapper, but improving the performance is not a goal of this work. - (New) Support what seems to be unintended ability for user space to provide parameters to "fill_buf" by making the parsing robust and only support changing parameters that are supported to be changed. Drop support for "write" operation since it has never been measured. - (New) Improve wraparound handling. (Ilpo) - (New) A couple of new fixes addressing issues discovered during development. - (Change from V1) To support fill_buf parameters provided by user space as well as test specific fill_buf parameters struct fill_buf_param is no longer just a member of struct resctrl_val_param, instead there could be at most two instances of struct fill_buf_param, the immutable parameters provided by user space and the parameters used by individual tests. (Ilpo) - Please see individual patches for detailed changes. V1 cover: The resctrl selftests for Memory Bandwidth Allocation (MBA) and Memory Bandwidth Monitoring (MBM) are failing on some (for example [1]) Emerald Rapids systems. The test failures result from the following two properties of these systems: 1) Emerald Rapids systems can have up to 320MB L3 cache. The resctrl MBA and MBM selftests measure memory traffic for which a hardcoded 250MB buffer has been sufficient so far. On platforms with L3 cache larger than the buffer, the buffer fits in the L3 cache and thus no/very little memory traffic is generated during the "memory bandwidth" tests. 2) Some platform features, for example RAS features or memory performance features that generate memory traffic may drive accesses that are counted differently by performance counters and MBM respectively, for instance generating "overhead" traffic which is not counted against any specific RMID. Until now these counting differences have always been "in the noise". On Emerald Rapids systems the maximum MBA throttling (10% memory bandwidth) throttles memory bandwidth to where memory accesses by these other platform features push the memory bandwidth difference between memory controller performance counters and resctrl (MBM) beyond the tests' hardcoded tolerance. Make the tests more robust against platform variations: 1) Let the buffer used by memory bandwidth tests be guided by the size of the L3 cache. 2) Larger buffers require longer initialization time before the buffer can be used to measurement. Rework the tests to ensure that buffer initialization is complete before measurements start. 3) Do not compare performance counters and MBM measurements at low bandwidth. The value of "low" is hardcoded to 750MiB based on measurements on Emerald Rapids, Sapphire Rapids, and Ice Lake systems. This limit is not applicable to AMD systems since it only applies to the MBA and MBM tests that are isolated to Intel. [1] https://ark.intel.com/content/www/us/en/ark/products/237261/intel-xeon-plat… Reinette Chatre (15): selftests/resctrl: Make functions only used in same file static selftests/resctrl: Print accurate buffer size as part of MBM results selftests/resctrl: Fix memory overflow due to unhandled wraparound selftests/resctrl: Protect against array overrun during iMC config parsing selftests/resctrl: Protect against array overflow when reading strings selftests/resctrl: Make wraparound handling obvious selftests/resctrl: Remove "once" parameter required to be false selftests/resctrl: Only support measured read operation selftests/resctrl: Remove unused measurement code selftests/resctrl: Make benchmark parameter passing robust selftests/resctrl: Ensure measurements skip initialization of default benchmark selftests/resctrl: Use cache size to determine "fill_buf" buffer size selftests/resctrl: Do not compare performance counters and resctrl at low bandwidth selftests/resctrl: Keep results from first test run selftests/resctrl: Replace magic constants used as array size tools/testing/selftests/resctrl/cmt_test.c | 37 +- tools/testing/selftests/resctrl/fill_buf.c | 45 +- tools/testing/selftests/resctrl/mba_test.c | 54 ++- tools/testing/selftests/resctrl/mbm_test.c | 37 +- tools/testing/selftests/resctrl/resctrl.h | 79 +++- .../testing/selftests/resctrl/resctrl_tests.c | 95 +++- tools/testing/selftests/resctrl/resctrl_val.c | 447 +++++------------- tools/testing/selftests/resctrl/resctrlfs.c | 19 +- 8 files changed, 354 insertions(+), 459 deletions(-) base-commit: 2a027d6bb66002c8e50e974676f932b33c5fce10 -- 2.47.0

1 year, 1 month

3
26
0 0

[PATCH v3 0/5] Improve arm64 pkeys handling in signal delivery

by Kevin Brodsky

This series is a follow-up to Joey's Permission Overlay Extension (POE) series [1] that recently landed on mainline. The goal is to improve the way we handle the register that governs which pkeys/POIndex are accessible (POR_EL0) during signal delivery. As things stand, we may unexpectedly fail to write the signal frame on the stack because POR_EL0 is not reset before the uaccess operations. See patch 1 for more details and the main changes this series brings. A similar series landed recently for x86/MPK [2]; the present series aims at aligning arm64 with x86. Worth noting: once the signal frame is written, POR_EL0 is still set to POR_EL0_INIT, granting access to pkey 0 only. This means that a program that sets up an alternate signal stack with a non-zero pkey will need some assembly trampoline to set POR_EL0 before invoking the real signal handler, as discussed here [3]. This is not ideal, but it makes experimentation with pkeys in signal handlers possible while waiting for a potential interface to control the pkey state when delivering a signal. See Pierre's reply [4] for more information about use-cases and a potential interface. The x86 series also added kselftests to ensure that no spurious SIGSEGV occurs during signal delivery regardless of which pkey is accessible at the point where the signal is delivered. This series adapts those kselftests to allow running them on arm64 (patch 4-5). There is a dependency on Yury's PKEY_UNRESTRICTED patch [7] for patch 4 specifically. Finally patch 2 is a clean-up following feedback on Joey's series [5]. I have tested this series on arm64 and x86_64 (booting and running the protection_keys and pkey_sighandler_tests mm kselftests). - Kevin --- v2..v3: * Reordered patches (patch 1 is now the main patch). * Patch 1: compute por_enable_all with an explicit loop, based on arch_max_pkey() (suggestion from Dave M). * Patch 4: improved naming, replaced global pkey reg value with inline helper, made use of Yury's PKEY_UNRESTRICTED macro [7] (suggestions from Dave H). v2: https://lore.kernel.org/linux-arm-kernel/20241023150511.3923558-1-kevin.bro… v1..v2: * In setup_rt_frame(), ensured that POR_EL0 is reset to its original value if we fail to deliver the signal (addresses Catalin's concern [6]). * Renamed *unpriv_access* to *user_access* in patch 3 (suggestion from Dave). * Made what patch 1-2 do explicit in the commit message body (suggestion from Dave). v1: https://lore.kernel.org/linux-arm-kernel/20241017133909.3837547-1-kevin.bro… [1] https://lore.kernel.org/linux-arm-kernel/20240822151113.1479789-1-joey.goul… [2] https://lore.kernel.org/lkml/20240802061318.2140081-1-aruna.ramakrishna@ora… [3] https://lore.kernel.org/lkml/CABi2SkWxNkP2O7ipkP67WKz0-LV33e5brReevTTtba6oK… [4] https://lore.kernel.org/linux-arm-kernel/87plns8owh.fsf@arm.com/ [5] https://lore.kernel.org/linux-arm-kernel/20241015114116.GA19334@willie-the-… [6] https://lore.kernel.org/linux-arm-kernel/Zw6D2waVyIwYE7wd@arm.com/ [7] https://lore.kernel.org/all/20241028090715.509527-2-yury.khrustalev@arm.com/ Cc: akpm(a)linux-foundation.org Cc: anshuman.khandual(a)arm.com Cc: aruna.ramakrishna(a)oracle.com Cc: broonie(a)kernel.org Cc: catalin.marinas(a)arm.com Cc: dave.hansen(a)linux.intel.com Cc: Dave.Martin(a)arm.com Cc: jeffxu(a)chromium.org Cc: joey.gouly(a)arm.com Cc: keith.lucas(a)oracle.com Cc: pierre.langlois(a)arm.com Cc: shuah(a)kernel.org Cc: sroettger(a)google.com Cc: tglx(a)linutronix.de Cc: will(a)kernel.org Cc: yury.khrustalev(a)arm.com Cc: linux-kselftest(a)vger.kernel.org Cc: x86(a)kernel.org Kevin Brodsky (5): arm64: signal: Improve POR_EL0 handling to avoid uaccess failures arm64: signal: Remove unnecessary check when saving POE state arm64: signal: Remove unused macro selftests/mm: Use generic pkey register manipulation selftests/mm: Enable pkey_sighandler_tests on arm64 arch/arm64/kernel/signal.c | 95 ++++++++++++--- tools/testing/selftests/mm/Makefile | 8 +- tools/testing/selftests/mm/pkey-arm64.h | 1 + tools/testing/selftests/mm/pkey-x86.h | 2 + .../selftests/mm/pkey_sighandler_tests.c | 115 ++++++++++++++---- 5 files changed, 176 insertions(+), 45 deletions(-) -- 2.43.0

1 year, 1 month

5
16
0 0

[PATCH v6 0/6] Add PSCI v1.3 SYSTEM_OFF2 support for hibernation

by David Woodhouse

The PSCI v1.3 spec (https://developer.arm.com/documentation/den0022) adds support for a SYSTEM_OFF2 function enabling a HIBERNATE_OFF state which is analogous to ACPI S4. This will allow hosting environments to determine that a guest is hibernated rather than just powered off, and ensure that they preserve the virtual environment appropriately to allow the guest to resume safely (or bump the hardware_signature in the FACS to trigger a clean reboot instead). This updates KVM to support advertising PSCI v1.3, and unconditionally enables the SYSTEM_OFF2 support when PSCI v1.3 is enabled. For the guest side, add a new SYS_OFF_MODE_POWER_OFF handler with higher priority than the EFI one, but which *only* triggers when there's a hibernation in progress. There are other ways to do this (see the commit message for more details) but this seemed like the simplest. Version 2 of the patch series splits out the psci.h definitions into a separate commit (a dependency for both the guest and KVM side), and adds definitions for the other new functions added in v1.3. It also moves the pKVM psci-relay support to a separate commit; although in arch/arm64/kvm that's actually about the *guest* side of SYSTEM_OFF2 (i.e. using it from the host kernel, relayed through nVHE). Version 3 dropped the KVM_CAP which allowed userspace to explicitly opt in to the new feature like with SYSTEM_SUSPEND, and makes it depend only on PSCI v1.3 being exposed to the guest. Version 4 is no longer RFC, as the PSCI v1.3 spec is finally published. Minor fixes from the last round of review, and an added KVM self test. Version 5 drops some of the changes which didn't make it to the final v1.3 spec, and cleans up a couple of places which still referred to it as 'alpha' or 'beta'. It also temporarily drops the guest-side patch to invoke SYSTEM_OFF2 for hibernation, pending confirmation that the final PSCI v1.3 spec just has a typo where it changed to saying that 0x1 should be passed to mean HIBERNATE_OFF, even though it's advertised as bit 0. That can be sent under separate cover, and perhaps should have been anyway. The change in question doesn't matter for any of the KVM patches, because we just treat SYSTEM_OFF2 like the existing SYSTEM_RESET2, setting a flag to indicate that it was a SYSTEM_OFF2 call, but not actually caring about the argument; that's for userspace to worry about. Version 6 is updated to revision F.b of the specification, allowing both 0x0 and 0x1 to indicate HIBERNATE_OFF in the SYSTEM_OFF2 call, as well as disallowing anything but zero in the second argument. The test is expanded to cover those variants, and to require PSCI v1.3 instead of skipping on older kernels. The final guest-side patch in the series is reinstated, using zero as the argument for compatibility with existing hypervisors in the field as permitted by revision F.b. allows for zero as well as 0x1 for HIBERNATE_OFF to accommodate the change in the final version of the spec, and expands the test to cover both forms as well as checking that a non-zero second argument is correctly rejected. David Woodhouse (6): firmware/psci: Add definitions for PSCI v1.3 specification KVM: arm64: Add PSCI v1.3 SYSTEM_OFF2 function for hibernation KVM: arm64: Add support for PSCI v1.2 and v1.3 KVM: selftests: Add test for PSCI SYSTEM_OFF2 KVM: arm64: nvhe: Pass through PSCI v1.3 SYSTEM_OFF2 call arm64: Use SYSTEM_OFF2 PSCI call to power off for hibernate Documentation/virt/kvm/api.rst | 11 +++ arch/arm64/include/uapi/asm/kvm.h | 6 ++ arch/arm64/kvm/hyp/nvhe/psci-relay.c | 2 + arch/arm64/kvm/hypercalls.c | 2 + arch/arm64/kvm/psci.c | 50 ++++++++++++- drivers/firmware/psci/psci.c | 42 +++++++++++ include/kvm/arm_psci.h | 4 +- include/uapi/linux/psci.h | 5 ++ kernel/power/hibernate.c | 5 +- tools/testing/selftests/kvm/aarch64/psci_test.c | 93 +++++++++++++++++++++++++ 10 files changed, 217 insertions(+), 3 deletions(-)

1 year, 1 month

6
28
0 0

[PATCH AUTOSEL 4.19 3/5] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index f1c6e025cbe54..561bcc253fb3e 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -152,7 +152,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 5.4 3/6] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index f45e510500c0d..09773695d219f 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -242,7 +242,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 5.10 3/6] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index f45e510500c0d..09773695d219f 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -242,7 +242,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 5.15 07/10] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index f45e510500c0d..09773695d219f 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -242,7 +242,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 6.1 07/11] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index f45e510500c0d..09773695d219f 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -242,7 +242,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 6.6 10/14] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index bc71cbca0dde7..a1f506ba55786 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -334,7 +334,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH AUTOSEL 6.11 15/21] selftests/watchdog-test: Fix system accidentally reset after watchdog-test

by Sasha Levin

From: Li Zhijian <lizhijian(a)fujitsu.com> [ Upstream commit dc1308bee1ed03b4d698d77c8bd670d399dcd04d ] When running watchdog-test with 'make run_tests', the watchdog-test will be terminated by a timeout signal(SIGTERM) due to the test timemout. And then, a system reboot would happen due to watchdog not stop. see the dmesg as below: ``` [ 1367.185172] watchdog: watchdog0: watchdog did not stop! ``` Fix it by registering more signals(including SIGTERM) in watchdog-test, where its signal handler will stop the watchdog. After that # timeout 1 ./watchdog-test Watchdog Ticking Away! . Stopping watchdog ticks... Link: https://lore.kernel.org/all/20241029031324.482800-1-lizhijian@fujitsu.com/ Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index bc71cbca0dde7..a1f506ba55786 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -334,7 +334,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH v6] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- V6: - make commit message cleaner V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - added selftest - fixed compile error V2: - fix fib_info_num_path parameter pass --- net/ipv4/route.c | 13 +++++ tools/testing/selftests/net/pmtu.sh | 78 ++++++++++++++++++++++++++++- 2 files changed, 90 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..41162b5cc4cb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..a0159340fe84 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -266,7 +266,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 0" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -2329,6 +2330,81 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing || return $ksft_skip + + ip nexthop ls >/dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "Nexthop objects not supported; skipping tests" + exit $ksft_skip + fi + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + dummy0_a="192.168.99.99" + dummy0_b="192.168.88.88" + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + #Set up host A with multipath routes to host B dummy0_b + run_cmd ${ns_a} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_a} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_a} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_a} ip link set dummy0 up + run_cmd ${ns_a} ip addr add ${dummy0_a} dev dummy0 + run_cmd ${ns_a} ip nexthop add id 201 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 202 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 203 group 201/202 + run_cmd ${ns_a} ip route add ${dummy0_b} nhid 203 + + #Set up host B with multipath routes to host A dummy0_a + run_cmd ${ns_b} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_b} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_b} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_b} ip link set dummy0 up + run_cmd ${ns_b} ip addr add ${dummy0_b} dev dummy0 + run_cmd ${ns_b} ip nexthop add id 201 via ${prefix4}.${b_r1}.2 dev veth_A-R1 + run_cmd ${ns_b} ip nexthop add id 202 via ${prefix4}.${b_r2}.2 dev veth_A-R2 + run_cmd ${ns_b} ip nexthop add id 203 group 201/202 + run_cmd ${ns_b} ip route add ${dummy0_a} nhid 203 + + #Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${dummy0_a} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_a} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${dummy0_b} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_b} via ${prefix4}.${b_r2}.1 + + + #Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dummy0_b}" + + #Do route lookup before checking cached exceptions + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R1 + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R2 + + #Check cached exceptions + if [ "$(${ns_a} ip -oneline route list cache| grep mtu | wc -l)" -ne 2 ]; then + err " there are not enough cached exceptions" + fail=1 + fi + + return ${fail} +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year, 1 month

2
3
0 0

[PATCH v4 1/2] selftests:tmpfs: Add Skip test if not run as root

by Shivam Chaudhary

- Add skip test if not run as root, with an appropriate Warning. - Add 'ksft_print_header()' and 'ksft_set_plan()' to structure test outputs more effectively. Test logs : Before change: - Without root error: unshare, errno 1 - With root No, output After change: - Without root TAP version 13 1..1 - With root TAP version 13 1..1 Signed-off-by: Shivam Chaudhary <cvam0000(a)gmail.com> --- Notes: Changes in v4 1/2: - Start a patchset - Split patch into smaller pathes to make it easy to review. link to v3: https://lore.kernel.org/all/20241028185756.111832-1-cvam0000@gmail.com/ Changes in v3: - Remove extra ksft_set_plan() - Remove function for unshare() - Fix the comment style link to v2: https://lore.kernel.org/all/20241026191621.2860376-1-cvam0000@gmail.com/ Changes in v2: - Make the commit message more clear. link to v1: https://lore.kernel.org/all/20241024200228.1075840-1-cvam0000@gmail.com/T/#u tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c index b5c3ddb90942..cdab1e8c0392 100644 --- a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c +++ b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c @@ -23,10 +23,23 @@ #include <sys/mount.h> #include <unistd.h> +#include "../kselftest.h" + int main(void) { int fd; + /* Setting up kselftest framework */ + ksft_print_header(); + ksft_set_plan(1); + + /* Check if test is run as root */ + if (geteuid()) { + ksft_print_msg("Skip : Need to run as root"); + exit(KSFT_SKIP); + + } + if (unshare(CLONE_NEWNS) == -1) { if (errno == ENOSYS || errno == EPERM) { fprintf(stderr, "error: unshare, errno %d\n", errno); -- 2.45.2

1 year, 1 month

1
0
0 0

[PATCH v3] selftests: clone3: Use the capget and capset syscall directly

by zhouyuhang

From: zhouyuhang <zhouyuhang(a)kylinos.cn> The libcap commit aca076443591 ("Make cap_t operations thread safe.") added a __u8 mutex at the beginning of the struct _cap_struct, it changes the offset of the members in the structure that breaks the assumption made in the "struct libcap" definition in clone3_cap_checkpoint_restore.c. This will cause the test case to fail with the following output: # RUN global.clone3_cap_checkpoint_restore ... # clone3() syscall supported # clone3_cap_checkpoint_restore.c:151:clone3_cap_checkpoint_restore:Child has PID 130508 cap_set_proc: Operation not permitted # clone3_cap_checkpoint_restore.c:160:clone3_cap_checkpoint_restore:Expected set_capability() (-1) == 0 (0) # clone3_cap_checkpoint_restore.c:161:clone3_cap_checkpoint_restore:Could not set CAP_CHECKPOINT_RESTORE # clone3_cap_checkpoint_restore: Test terminated by assertion # FAIL global.clone3_cap_checkpoint_restore Changing to using capget and capset syscall directly here can fix this error, just like what the commit 663af70aabb7 ("bpf: selftests: Add helpers to directly use the capget and capset syscall") does. Signed-off-by: zhouyuhang <zhouyuhang(a)kylinos.cn> --- .../clone3/clone3_cap_checkpoint_restore.c | 58 +++++++++---------- 1 file changed, 27 insertions(+), 31 deletions(-) diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 3c196fa86c99..8b61702bf721 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -27,6 +27,13 @@ #include "../kselftest_harness.h" #include "clone3_selftests.h" +/* + * Prevent not being defined in the header file + */ +#ifndef CAP_CHECKPOINT_RESTORE +#define CAP_CHECKPOINT_RESTORE 40 +#endif + static void child_exit(int ret) { fflush(stdout); @@ -87,47 +94,36 @@ static int test_clone3_set_tid(struct __test_metadata *_metadata, return ret; } -struct libcap { - struct __user_cap_header_struct hdr; - struct __user_cap_data_struct data[2]; -}; - static int set_capability(void) { - cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID }; - struct libcap *cap; - int ret = -1; - cap_t caps; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); + struct __user_cap_data_struct data[2]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = 1 << CAP_SETUID | 1 << CAP_SETGID; + __u32 cap1 = 1 << (CAP_CHECKPOINT_RESTORE - 32); + int ret; + + ret = capget(&hdr, data); + if (ret) { + perror("capget"); return -1; } /* Drop all capabilities */ - if (cap_clear(caps)) { - perror("cap_clear"); - goto out; - } - - cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET); - cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET); + memset(&data, 0, sizeof(data)); - cap = (struct libcap *) caps; + data[0].effective |= cap0; + data[0].permitted |= cap0; - /* 40 -> CAP_CHECKPOINT_RESTORE */ - cap->data[1].effective |= 1 << (40 - 32); - cap->data[1].permitted |= 1 << (40 - 32); + data[1].effective |= cap1; + data[1].permitted |= cap1; - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; + ret = capset(&hdr, data); + if (ret) { + perror("capset"); + return -1; } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); return ret; } -- 2.27.0

1 year, 1 month

2
2
0 0

[PATCH net-next] selftests/tc-testing: add tests for qdisc_tree_reduce_backlog

by Pedro Tammela

Add 3 tests to check for the expected behaviour of qdisc_tree_reduce_backlog in special scenarios. - The first test checks if the qdisc class is notified of deletion for major handle 'ffff:'. - The second test checks the same as the first test but with 'ffff:' as the root qdisc. - The third test checks if everything works if ingress is active. Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Signed-off-by: Pedro Tammela <pctammela(a)mojatatu.com> --- .../tc-testing/tc-tests/infra/qdiscs.json | 98 +++++++++++++++++++ 1 file changed, 98 insertions(+) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json new file mode 100644 index 000000000000..d3dd65b05b5f --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -0,0 +1,98 @@ +[ + { + "id": "ca5e", + "name": "Check class delete notification for ffff:", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle ffff: drr", + "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr", + "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true", + "$TC class del dev $DUMMY classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -s qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + }, + { + "id": "e4b7", + "name": "Check class delete notification for root ffff:", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle ffff: drr", + "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr", + "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true", + "$TC class del dev $DUMMY classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr ffff: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle ffff: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + }, + { + "id": "33a9", + "name": "Check ingress is not searchable on backlog update", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY ingress", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: drr", + "$TC filter add dev $DUMMY parent 2: basic classid 2:1", + "$TC class add dev $DUMMY parent 2: classid 2:1 drr", + "$TC qdisc add dev $DUMMY parent 2:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true" + ], + "cmdUnderTest": "$TC class del dev $DUMMY classid 2:1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$TC qdisc del dev $DUMMY ingress", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + } +] -- 2.43.0

1 year, 1 month

3
2
0 0

[PATCH net-next v5 0/7] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v5, see changelog below. Note that our performance tests were not re-run for this revision as we updated a commit message, fixed typos, removed a short unnecessary paragraph from the documentation and added a very minor functional change to return without suspended IRQs in certain error cases. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. We've added an additional test case, 'fullbusy', achieved by modifying libevent for comparison. See below for a detailed description, link to the patch, and test results. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Design rationale The implementation of the IRQ suspension mechanism very nicely dovetails with the existing mechanism for IRQ deferral when preferred busy poll is enabled (introduced in commit 7fd3253a7de6 ("net: Introduce preferred busy-polling"), see that commit message for more details). While it would be possible to inject the suspend timeout via the existing epoll ioctl, it is more natural to avoid this path for one main reason: An epoll context is linked to NAPI IDs as file descriptors are added; this means any epoll context might suddenly be associated with a different net_device if the application were to replace all existing fds with fds from a different device. In this case, the scope of the suspend timeout becomes unclear and many edge cases for both the user application and the kernel are introduced Only a single iteration through napi busy polling is needed for this mechanism to work effectively. Since an important objective for this mechanism is preserving cpu cycles, exactly one iteration of the napi busy loop is invoked when busy_poll_usecs is set to 0. ~ Important call out in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over at least 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results are higher than our previous submission, but the relative differences between variants are equivalent. Because the patches have been rebased on 6.12, several factors have likely influenced the overall performance. Most importantly, we had to switch to a new set of basic kernel options, which has likely altered the baseline performance. Because the overall comparison of variants still holds, we have not attempted to recreate the exact set of kernel options from the previous submission. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 200024 127 254 458 25 12748 11289 defer10 200K 199991 64 128 166 27 18763 16574 defer20 200K 199986 72 135 178 25 15405 14173 defer50 200K 200025 91 149 198 23 12275 12203 defer200 200K 199996 182 266 326 18 8595 9183 fullbusy 200K 200040 58 123 167 100 43641 23145 napibusy 200K 200009 115 244 299 56 24797 24693 suspend10 200K 200005 63 128 167 32 19559 17240 suspend20 200K 199952 69 132 170 29 16324 14838 suspend50 200K 200019 84 144 189 26 13106 12516 suspend200 200K 199978 168 264 326 20 9331 9643 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400017 157 292 762 39 9287 9325 defer10 400K 400033 71 141 204 53 13950 12943 defer20 400K 399935 79 150 212 47 12027 11673 defer50 400K 399888 101 171 231 39 9556 9921 defer200 400K 399993 200 287 358 32 7428 8576 fullbusy 400K 400018 63 132 203 100 21827 16062 napibusy 400K 399970 89 230 292 83 18156 16508 suspend10 400K 400061 69 139 202 54 13576 13057 suspend20 400K 399988 73 144 206 49 11930 11773 suspend50 400K 399975 88 161 218 42 9996 10270 suspend200 400K 399954 172 276 353 34 7847 8713 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 600031 166 289 631 61 9188 8787 defer10 600K 599967 85 167 262 75 11833 10947 defer20 600K 599888 89 165 243 66 10513 10362 defer50 600K 600072 109 185 253 55 8664 9190 defer200 600K 599951 222 315 393 45 6892 8213 fullbusy 600K 600041 69 145 227 100 14549 13936 napibusy 600K 599980 79 188 280 96 13927 14155 suspend10 600K 600028 78 159 267 69 10877 11032 suspend20 600K 600026 81 159 254 64 9922 10320 suspend50 600K 600007 96 178 258 57 8681 9331 suspend200 600K 599964 177 295 369 47 7115 8366 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800034 198 329 698 84 9366 8338 defer10 800K 799718 243 642 1457 95 10532 9007 defer20 800K 800009 132 245 399 89 9956 8979 defer50 800K 800024 136 228 378 80 9002 8598 defer200 800K 799965 255 362 473 66 7481 8147 fullbusy 800K 799927 78 157 253 100 10915 12533 napibusy 800K 799870 81 173 273 99 10826 12532 suspend10 800K 799991 84 167 269 83 9380 9802 suspend20 800K 799979 90 172 290 78 8765 9404 suspend50 800K 800031 106 191 307 71 7945 8805 suspend200 800K 799905 182 307 411 62 6985 8242 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 919543 3805 6390 14229 98 9324 7978 defer10 1000K 850751 4574 7382 15370 99 10218 8470 defer20 1000K 890296 4736 6862 14858 99 9708 8277 defer50 1000K 932694 3463 6180 13251 97 9148 8053 defer200 1000K 951311 3524 6052 13599 96 8875 7845 fullbusy 1000K 1000011 90 181 278 100 8731 10686 napibusy 1000K 1000050 93 184 280 100 8721 10547 suspend10 1000K 999962 101 193 306 92 8138 8980 suspend20 1000K 1000030 103 191 324 88 7844 8763 suspend50 1000K 1000001 114 202 320 83 7396 8431 suspend200 1000K 999965 185 314 428 76 6733 8072 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1005592 4651 6594 14979 100 8679 7918 defer10 MAX 928204 5106 7286 15199 100 9398 8380 defer20 MAX 984663 4774 6518 14920 100 8861 8063 defer50 MAX 1044099 4431 6368 14652 100 8350 7948 defer200 MAX 1040451 4423 6610 14674 100 8380 7931 fullbusy MAX 1236608 3715 3987 12805 100 7051 7936 napibusy MAX 1077516 4345 10155 15957 100 8080 7842 suspend10 MAX 1218344 3760 3990 12585 100 7150 7935 suspend20 MAX 1220056 3752 4053 12602 100 7150 7961 suspend50 MAX 1213666 3791 4103 12919 100 7183 7959 suspend200 MAX 1217411 3768 3988 12863 100 7161 7954 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2) can take control from Loop 1), if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2) and 3) "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2), which essentially tilts this in favour of Loop 3). If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3) cannot take control from Loop 1). Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. We ran experiments with these parameters set to zero and the results are as expected and essentially the same as the base case. - Can the new timeout value be threaded through the new epoll ioctl ? Only with difficulty. The epoll ioctl sets options on an epoll context and the NAPI ID associated with an epoll context can change based on what file descriptors a user app adds to the epoll context. This would introduce complexity in the API from the user perspective and also complexity in the kernel. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the results. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v5: - Adjusted patch 5 to only suspend IRQs when ep_send_events returns a positive return value. This issue was pointed out by Hillf Danton. - Updated the commit message of patch 6 which still mentioned netcat, despite the code being updated in v4 to replace it with socat and fixed misspelling of netdevsim. - Fixed a minor typo in patch 7 and removed an unnecessary paragraph. - Added Sridhar Samudrala's Reviewed-by to patch 1-5 and 7. v4: https://lore.kernel.org/netdev/20241102005214.32443-1-jdamato@fastly.com/ - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: https://lore.kernel.org/netdev/20241101004846.32532-1-jdamato@fastly.com/ - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (5): net: Add napi_struct parameter irq_suspend_timeout net: Suspend softirq when prefer_busy_poll is set net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 172 ++++++++- fs/eventpoll.c | 36 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 58 +++- net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 164 +++++++++ tools/testing/selftests/net/busy_poller.c | 328 ++++++++++++++++++ 15 files changed, 807 insertions(+), 11 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dbb9a7ef347828870df3e5e6ddf19469a3277fc9 -- 2.25.1

1 year, 1 month

1
1
0 0

[PATCH v1 1/2] selftests/x86/syscall: fix coccinelle WARNING recommending the use of ARRAY_SIZE()

by Mirsad Todorovac

Coccinelle gives WARNING recommending the use of ARRAY_SIZE() macro definition to improve the code readability: ./tools/testing/selftests/x86/syscall_numbering.c:316:35-36: WARNING: Use ARRAY_SIZE Fixes: 15c82d98a0f78 ("selftests/x86/syscall: Update and extend syscall_numbering_64") Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: x86(a)kernel.org Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Mirsad Todorovac <mtodorovac69(a)gmail.com> --- v1: initial version. tools/testing/selftests/x86/syscall_numbering.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/x86/syscall_numbering.c b/tools/testing/selftests/x86/syscall_numbering.c index 991591718bb0..41c42b7b54a6 100644 --- a/tools/testing/selftests/x86/syscall_numbering.c +++ b/tools/testing/selftests/x86/syscall_numbering.c @@ -25,6 +25,7 @@ #include <sys/mman.h> #include <linux/ptrace.h> +#include "../kselftest.h" /* Common system call numbers */ #define SYS_READ 0 @@ -313,7 +314,7 @@ static void test_syscall_numbering(void) * The MSB is supposed to be ignored, so we loop over a few * to test that out. */ - for (size_t i = 0; i < sizeof(msbs)/sizeof(msbs[0]); i++) { + for (size_t i = 0; i < ARRAY_SIZE(msbs); i++) { int msb = msbs[i]; run("Checking system calls with msb = %d (0x%x)\n", msb, msb); -- 2.43.0

1 year, 1 month

3
5
0 0

[PATCH v5] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. V5: - make self test cleaner V4: - fix selftest, do route lookup before checking cached exceptions V3: - added selftest - fixed compile error V2: - fix fib_info_num_path parameter pass An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- net/ipv4/route.c | 13 +++++ tools/testing/selftests/net/pmtu.sh | 78 ++++++++++++++++++++++++++++- 2 files changed, 90 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..41162b5cc4cb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..a0159340fe84 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -266,7 +266,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 0" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -2329,6 +2330,81 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing || return $ksft_skip + + ip nexthop ls >/dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "Nexthop objects not supported; skipping tests" + exit $ksft_skip + fi + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + dummy0_a="192.168.99.99" + dummy0_b="192.168.88.88" + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + #Set up host A with multipath routes to host B dummy0_b + run_cmd ${ns_a} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_a} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_a} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_a} ip link set dummy0 up + run_cmd ${ns_a} ip addr add ${dummy0_a} dev dummy0 + run_cmd ${ns_a} ip nexthop add id 201 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 202 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 203 group 201/202 + run_cmd ${ns_a} ip route add ${dummy0_b} nhid 203 + + #Set up host B with multipath routes to host A dummy0_a + run_cmd ${ns_b} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_b} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_b} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_b} ip link set dummy0 up + run_cmd ${ns_b} ip addr add ${dummy0_b} dev dummy0 + run_cmd ${ns_b} ip nexthop add id 201 via ${prefix4}.${b_r1}.2 dev veth_A-R1 + run_cmd ${ns_b} ip nexthop add id 202 via ${prefix4}.${b_r2}.2 dev veth_A-R2 + run_cmd ${ns_b} ip nexthop add id 203 group 201/202 + run_cmd ${ns_b} ip route add ${dummy0_a} nhid 203 + + #Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${dummy0_a} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_a} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${dummy0_b} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_b} via ${prefix4}.${b_r2}.1 + + + #Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dummy0_b}" + + #Do route lookup before checking cached exceptions + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R1 + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R2 + + #Check cached exceptions + if [ "$(${ns_a} ip -oneline route list cache| grep mtu | wc -l)" -ne 2 ]; then + err " there are not enough cached exceptions" + fail=1 + fi + + return ${fail} +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year, 1 month

3
4
0 0

[PATCH 0/2] kunit: enable hardware virtualization

by Tamir Duberstein

This series implements feature detection of hardware virtualization on Linux and macOS; the latter being my primary use case. This yields approximately a 6x improvement using HVF on M3 Pro. Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Tamir Duberstein (2): kunit: add fallback for os.sched_getaffinity kunit: enable hardware acceleration when available tools/testing/kunit/kunit.py | 11 ++++++++++- tools/testing/kunit/kunit_kernel.py | 26 +++++++++++++++++++++++++- tools/testing/kunit/qemu_configs/arm64.py | 2 +- 3 files changed, 36 insertions(+), 3 deletions(-) --- base-commit: ae90f6a6170d7a7a1aa4fddf664fbd093e3023bc change-id: 20241025-kunit-qemu-accel-macos-2840e4c2def5 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

1 year, 1 month

3
6
0 0

[GIT PULL] Kselftest fixes update for Linux 6.12-rc6

by Shuah Khan

Hi Linus, Please pull the following kselftest fixes update for Linux 6.12-rc6. Kselftest fixes for Linux 6.12-rc6 - fix syntax error in frequency calculation arithmetic expression in intel_pstate run.sh - add missing cpupower dependency check intel_pstate run.sh - fix idmap_mount_tree_invalid test failure due to incorrect argument - fix watchdog-test run leaving the watchdog timer enabled causing system reboot. With this fix, the test disables the watchdog timer when it gets terminated with SIGTERM, SIGKILL, and SIGQUIT in addition to SIGINT diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit fe05c40ca9c18cfdb003f639a30fc78a7ab49519: selftest: hid: add the missing tests directory (2024-10-16 15:55:14 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-fixes-6.12-rc6 for you to fetch changes up to dc1308bee1ed03b4d698d77c8bd670d399dcd04d: selftests/watchdog-test: Fix system accidentally reset after watchdog-test (2024-10-28 21:34:43 -0600) ---------------------------------------------------------------- linux_kselftest-fixes-6.12-rc6 Kselftest fixes for Linux 6.12-rc6 - fix syntax error in frequency calculation arithmetic expression in intel_pstate run.sh - add missing cpupower dependency check intel_pstate run.sh - fix idmap_mount_tree_invalid test failure due to incorrect argument - fix watchdog-test run leaving the watchdog timer enabled causing system reboot. With this fix, the test disables the watchdog timer when it gets terminated with SIGTERM, SIGKILL, and SIGQUIT in addition to SIGINT ---------------------------------------------------------------- Alessandro Zanni (2): selftests/intel_pstate: fix operand expected error selftests/intel_pstate: check if cpupower is installed Li Zhijian (1): selftests/watchdog-test: Fix system accidentally reset after watchdog-test zhouyuhang (1): selftests/mount_setattr: fix idmap_mount_tree_invalid failed to run tools/testing/selftests/intel_pstate/run.sh | 9 +++++++-- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 9 +++++++++ tools/testing/selftests/watchdog/watchdog-test.c | 6 ++++++ 3 files changed, 22 insertions(+), 2 deletions(-) ---------------------------------------------------------------

1 year, 1 month

2
1
0 0

[PATCH net-next v4 0/7] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v4, see changelog below. Note that our performance tests were not re-run for this revision as we updated the selftest, FAQ in the cover letter, and kernel documentation. No functional/code changes. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. We've added an additional test case, 'fullbusy', achieved by modifying libevent for comparison. See below for a detailed description, link to the patch, and test results. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Design rationale The implementation of the IRQ suspension mechanism very nicely dovetails with the existing mechanism for IRQ deferral when preferred busy poll is enabled (introduced in commit 7fd3253a7de6 ("net: Introduce preferred busy-polling"), see that commit message for more details). While it would be possible to inject the suspend timeout via the existing epoll ioctl, it is more natural to avoid this path for one main reason: An epoll context is linked to NAPI IDs as file descriptors are added; this means any epoll context might suddenly be associated with a different net_device if the application were to replace all existing fds with fds from a different device. In this case, the scope of the suspend timeout becomes unclear and many edge cases for both the user application and the kernel are introduced Only a single iteration through napi busy polling is needed for this mechanism to work effectively. Since an important objective for this mechanism is preserving cpu cycles, exactly one iteration of the napi busy loop is invoked when busy_poll_usecs is set to 0. ~ Important call outs in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. - Patches apply cleanly on commit 160a810b2a85 ("net: vxlan: update the document for vxlan_snoop()"). ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over at least 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results are higher than our previous submission, but the relative differences between variants are equivalent. Because the patches have been rebased on 6.12, several factors have likely influenced the overall performance. Most importantly, we had to switch to a new set of basic kernel options, which has likely altered the baseline performance. Because the overall comparison of variants still holds, we have not attempted to recreate the exact set of kernel options from the previous submission. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 200024 127 254 458 25 12748 11289 defer10 200K 199991 64 128 166 27 18763 16574 defer20 200K 199986 72 135 178 25 15405 14173 defer50 200K 200025 91 149 198 23 12275 12203 defer200 200K 199996 182 266 326 18 8595 9183 fullbusy 200K 200040 58 123 167 100 43641 23145 napibusy 200K 200009 115 244 299 56 24797 24693 suspend10 200K 200005 63 128 167 32 19559 17240 suspend20 200K 199952 69 132 170 29 16324 14838 suspend50 200K 200019 84 144 189 26 13106 12516 suspend200 200K 199978 168 264 326 20 9331 9643 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400017 157 292 762 39 9287 9325 defer10 400K 400033 71 141 204 53 13950 12943 defer20 400K 399935 79 150 212 47 12027 11673 defer50 400K 399888 101 171 231 39 9556 9921 defer200 400K 399993 200 287 358 32 7428 8576 fullbusy 400K 400018 63 132 203 100 21827 16062 napibusy 400K 399970 89 230 292 83 18156 16508 suspend10 400K 400061 69 139 202 54 13576 13057 suspend20 400K 399988 73 144 206 49 11930 11773 suspend50 400K 399975 88 161 218 42 9996 10270 suspend200 400K 399954 172 276 353 34 7847 8713 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 600031 166 289 631 61 9188 8787 defer10 600K 599967 85 167 262 75 11833 10947 defer20 600K 599888 89 165 243 66 10513 10362 defer50 600K 600072 109 185 253 55 8664 9190 defer200 600K 599951 222 315 393 45 6892 8213 fullbusy 600K 600041 69 145 227 100 14549 13936 napibusy 600K 599980 79 188 280 96 13927 14155 suspend10 600K 600028 78 159 267 69 10877 11032 suspend20 600K 600026 81 159 254 64 9922 10320 suspend50 600K 600007 96 178 258 57 8681 9331 suspend200 600K 599964 177 295 369 47 7115 8366 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800034 198 329 698 84 9366 8338 defer10 800K 799718 243 642 1457 95 10532 9007 defer20 800K 800009 132 245 399 89 9956 8979 defer50 800K 800024 136 228 378 80 9002 8598 defer200 800K 799965 255 362 473 66 7481 8147 fullbusy 800K 799927 78 157 253 100 10915 12533 napibusy 800K 799870 81 173 273 99 10826 12532 suspend10 800K 799991 84 167 269 83 9380 9802 suspend20 800K 799979 90 172 290 78 8765 9404 suspend50 800K 800031 106 191 307 71 7945 8805 suspend200 800K 799905 182 307 411 62 6985 8242 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 919543 3805 6390 14229 98 9324 7978 defer10 1000K 850751 4574 7382 15370 99 10218 8470 defer20 1000K 890296 4736 6862 14858 99 9708 8277 defer50 1000K 932694 3463 6180 13251 97 9148 8053 defer200 1000K 951311 3524 6052 13599 96 8875 7845 fullbusy 1000K 1000011 90 181 278 100 8731 10686 napibusy 1000K 1000050 93 184 280 100 8721 10547 suspend10 1000K 999962 101 193 306 92 8138 8980 suspend20 1000K 1000030 103 191 324 88 7844 8763 suspend50 1000K 1000001 114 202 320 83 7396 8431 suspend200 1000K 999965 185 314 428 76 6733 8072 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1005592 4651 6594 14979 100 8679 7918 defer10 MAX 928204 5106 7286 15199 100 9398 8380 defer20 MAX 984663 4774 6518 14920 100 8861 8063 defer50 MAX 1044099 4431 6368 14652 100 8350 7948 defer200 MAX 1040451 4423 6610 14674 100 8380 7931 fullbusy MAX 1236608 3715 3987 12805 100 7051 7936 napibusy MAX 1077516 4345 10155 15957 100 8080 7842 suspend10 MAX 1218344 3760 3990 12585 100 7150 7935 suspend20 MAX 1220056 3752 4053 12602 100 7150 7961 suspend50 MAX 1213666 3791 4103 12919 100 7183 7959 suspend200 MAX 1217411 3768 3988 12863 100 7161 7954 ~ FAQ - Why is a new parameter needed? Does irq_suspend_timeout override gro_flush_timeout? Using the suspend mechanism causes the system to alternate between polling mode and irq-driven packet delivery. During busy periods, irq_suspend_timeout overrides gro_flush_timeout and keeps the system busy polling, but when epoll finds no events, the setting of gro_flush_timeout and napi_defer_hard_irqs determine the next step. There are essentially three possible loops for network processing and packet delivery: 1) hardirq -> softirq -> napi poll; basic interrupt delivery 2) timer -> softirq -> napi poll; deferred irq processing 3) epoll -> busy-poll -> napi poll; busy looping Loop 2) can take control from Loop 1), if gro_flush_timeout and napi_defer_hard_irqs are set. If gro_flush_timeout and napi_defer_hard_irqs are set, Loops 2) and 3) "wrestle" with each other for control. During busy periods, irq_suspend_timeout is used as timer in Loop 2), which essentially tilts this in favour of Loop 3). If gro_flush_timeout and napi_defer_hard_irqs are not set, Loop 3) cannot take control from Loop 1). Therefore, setting gro_flush_timeout and napi_defer_hard_irqs is the recommended usage, because otherwise setting irq_suspend_timeout might not have any discernible effect. We ran experiments with these parameters set to zero and the results are as expected and essentially the same as the base case. - Can the new timeout value be threaded through the new epoll ioctl ? Only with difficulty. The epoll ioctl sets options on an epoll context and the NAPI ID associated with an epoll context can change based on what file descriptors a user app adds to the epoll context. This would introduce complexity in the API from the user perspective and also complexity in the kernel. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the result. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v4: - Added a new FAQ item to cover letter. - Updated patch 6 to use socat instead of nc in busy_poll_test.sh and updated busy_poller.c to use netlink directly to configure napi params. - Updated the kernel documentation in patch 7 to include more details. - Dropped Stanislav's Acked-by and Bagas' Reviewed-by from patch 7 since the documentation was updated. v3: - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (5): net: Add napi_struct parameter irq_suspend_timeout net: Suspend softirq when prefer_busy_poll is set net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 176 +++++++++- fs/eventpoll.c | 35 +- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 58 +++- net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/busy_poll_test.sh | 164 +++++++++ tools/testing/selftests/net/busy_poller.c | 328 ++++++++++++++++++ 15 files changed, 810 insertions(+), 11 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: dbb9a7ef347828870df3e5e6ddf19469a3277fc9 -- 2.25.1

1 year, 1 month

1
1
0 0

[PATCH net-next v3 0/7] Suspend IRQs during application busy periods

by Joe Damato

Greetings: Welcome to v3, see changelog below. Note that our performance tests were not re-run for this revision as we only updated a commit message and added a selftest. This series introduces a new mechanism, IRQ suspension, which allows network applications using epoll to mask IRQs during periods of high traffic while also reducing tail latency (compared to existing mechanisms, see below) during periods of low traffic. In doing so, this balances CPU consumption with network processing efficiency. Martin Karsten (CC'd) and I have been collaborating on this series for several months and have appreciated the feedback from the community on our RFC [1]. We've updated the cover letter and kernel documentation in an attempt to more clearly explain how this mechanism works, how applications can use it, and how it compares to existing mechanisms in the kernel. We've added an additional test case, 'fullbusy', achieved by modifying libevent for comparison. See below for a detailed description, link to the patch, and test results. I briefly mentioned this idea at netdev conf 2024 (for those who were there) and Martin described this idea in an earlier paper presented at Sigmetrics 2024 [2]. ~ The short explanation (TL;DR) We propose adding a new napi config parameter: irq_suspend_timeout to help balance CPU usage and network processing efficiency when using IRQ deferral and napi busy poll. If this parameter is set to a non-zero value *and* a user application has enabled preferred busy poll on a busy poll context (via the EPIOCSPARAMS ioctl introduced in commit 18e2bf0edf4d ("eventpoll: Add epoll ioctl for epoll_params")), then application calls to epoll_wait for that context will cause device IRQs and softirq processing to be suspended as long as epoll_wait successfully retrieves data from the NAPI. Each time data is retrieved, the irq_suspend_timeout is deferred. If/when network traffic subsides and epoll_wait returns no data, IRQ suspension is immediately reverted back to the existing napi_defer_hard_irqs and gro_flush_timeout mechanism which was introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")). The irq_suspend_timeout serves as a safety mechanism. If userland takes a long time processing data, irq_suspend_timeout will fire and restart normal NAPI processing. For a more in depth explanation, please continue reading. ~ Comparison with existing mechanisms Interrupt mitigation can be accomplished in napi software, by setting napi_defer_hard_irqs and gro_flush_timeout, or via interrupt coalescing in the NIC. This can be quite efficient, but in both cases, a fixed timeout (or packet count) needs to be configured. However, a fixed timeout cannot effectively support both low- and high-load situations: At low load, an application typically processes a few requests and then waits to receive more input data. In this scenario, a large timeout will cause unnecessary latency. At high load, an application typically processes many requests before being ready to receive more input data. In this case, a small timeout will likely fire prematurely and trigger irq/softirq processing, which interferes with the application's execution. This causes overhead, most likely due to cache contention. While NICs attempt to provide adaptive interrupt coalescing schemes, these cannot properly take into account application-level processing. An alternative packet delivery mechanism is busy-polling, which results in perfect alignment of application processing and network polling. It delivers optimal performance (throughput and latency), but results in 100% cpu utilization and is thus inefficient for below-capacity workloads. We propose to add a new packet delivery mode that properly alternates between busy polling and interrupt-based delivery depending on busy and idle periods of the application. During a busy period, the system operates in busy-polling mode, which avoids interference. During an idle period, the system falls back to interrupt deferral, but with a small timeout to avoid excessive latencies. This delivery mode can also be viewed as an extension of basic interrupt deferral, but alternating between a small and a very large timeout. This delivery mode is efficient, because it avoids softirq execution interfering with application processing during busy periods. It can be used with blocking epoll_wait to conserve cpu cycles during idle periods. The effect of alternating between busy and idle periods is that performance (throughput and latency) is very close to full busy polling, while cpu utilization is lower and very close to interrupt mitigation. ~ Usage details IRQ suspension is introduced via a per-NAPI configuration parameter that controls the maximum time that IRQs can be suspended. Here's how it is intended to work: - The user application (or system administrator) uses the netdev-genl netlink interface to set the pre-existing napi_defer_hard_irqs and gro_flush_timeout NAPI config parameters to enable IRQ deferral. - The user application (or system administrator) sets the proposed irq_suspend_timeout parameter via the netdev-genl netlink interface to a larger value than gro_flush_timeout to enable IRQ suspension. - The user application issues the existing epoll ioctl to set the prefer_busy_poll flag on the epoll context. - The user application then calls epoll_wait to busy poll for network events, as it normally would. - If epoll_wait returns events to userland, IRQs are suspended for the duration of irq_suspend_timeout. - If epoll_wait finds no events and the thread is about to go to sleep, IRQ handling using napi_defer_hard_irqs and gro_flush_timeout is resumed. As long as epoll_wait is retrieving events, IRQs (and softirq processing) for the NAPI being polled remain disabled. When network traffic reduces, eventually a busy poll loop in the kernel will retrieve no data. When this occurs, regular IRQ deferral using gro_flush_timeout for the polled NAPI is re-enabled. Unless IRQ suspension is continued by subsequent calls to epoll_wait, it automatically times out after the irq_suspend_timeout timer expires. Regular deferral is also immediately re-enabled when the epoll context is destroyed. ~ Usage scenario The target scenario for IRQ suspension as packet delivery mode is a system that runs a dominant application with substantial network I/O. The target application can be configured to receive input data up to a certain batch size (via epoll_wait maxevents parameter) and this batch size determines the worst-case latency that application requests might experience. Because packet delivery is suspended during the target application's processing, the batch size also determines the worst-case latency of concurrent applications using the same RX queue(s). gro_flush_timeout should be set as small as possible, but large enough to make sure that a single request is likely not being interfered with. irq_suspend_timeout is largely a safety mechanism against misbehaving applications. It should be set large enough to cover the processing of an entire application batch, i.e., the factor between gro_flush_timeout and irq_suspend_timeout should roughly correspond to the maximum batch size that the target application would process in one go. ~ Design rationale The implementation of the IRQ suspension mechanism very nicely dovetails with the existing mechanism for IRQ deferral when preferred busy poll is enabled (introduced in commit 7fd3253a7de6 ("net: Introduce preferred busy-polling"), see that commit message for more details). While it would be possible to inject the suspend timeout via the existing epoll ioctl, it is more natural to avoid this path for one main reason: An epoll context is linked to NAPI IDs as file descriptors are added; this means any epoll context might suddenly be associated with a different net_device if the application were to replace all existing fds with fds from a different device. In this case, the scope of the suspend timeout becomes unclear and many edge cases for both the user application and the kernel are introduced Only a single iteration through napi busy polling is needed for this mechanism to work effectively. Since an important objective for this mechanism is preserving cpu cycles, exactly one iteration of the napi busy loop is invoked when busy_poll_usecs is set to 0. ~ Important call outs in the implementation - Enabling per epoll-context preferred busy poll will now effectively lead to a nonblocking iteration through napi_busy_loop, even when busy_poll_usecs is 0. See patch 4. - Patches apply cleanly on commit 160a810b2a85 ("net: vxlan: update the document for vxlan_snoop()"). ~ Benchmark configs & descriptions The changes were benchmarked with memcached [3] using the benchmarking tool mutilate [4]. To facilitate benchmarking, a small patch [5] was applied to memcached 1.6.29 to allow setting per-epoll context preferred busy poll and other settings via environment variables. Another small patch [6] was applied to libevent to enable full busy-polling. Multiple scenarios were benchmarked as described below and the scripts used for producing these results can be found on github [7] (note: all scenarios use NAPI-based traffic splitting via SO_INCOMING_ID by passing -N to memcached): - base: - no other options enabled - deferX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - napibusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 200,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 64, busy_poll_budget = 64, prefer_busy_poll = true) - fullbusy: - set defer_hard_irqs to 100 - set gro_flush_timeout to 5,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 1000, busy_poll_budget = 64, prefer_busy_poll = true) - change memcached's nonblocking epoll_wait invocation (via libevent) to using a 1 ms timeout - suspendX: - set defer_hard_irqs to 100 - set gro_flush_timeout to X,000 - set irq_suspend_timeout to 20,000,000 - enable busy poll via the existing ioctl (busy_poll_usecs = 0, busy_poll_budget = 64, prefer_busy_poll = true) ~ Benchmark results Tested on: Single socket AMD EPYC 7662 64-Core Processor Hyperthreading disabled 4 NUMA Zones (NPS=4) 16 CPUs per NUMA zone (64 cores total) 2 x Dual port 100gbps Mellanox Technologies ConnectX-5 Ex EN NIC The test machine is configured such that a single interface has 8 RX queues. The queues' IRQs and memcached are pinned to CPUs that are NUMA-local to the interface which is under test. The NIC's interrupt coalescing configuration is left at boot-time defaults. Results: Results are shown below. The mechanism added by this series is represented by the 'suspend' cases. Data presented shows a summary over at least 10 runs of each test case [8] using the scripts on github [7]. For latency, the median is shown. For throughput and CPU utilization, the average is shown. The results also include cycles-per-query (cpq) and instruction-per-query (ipq) metrics, following the methodology proposed in [2], to augment the CPU utilization numbers, which could be skewed due to frequency scaling. We find that this does not appear to be the case as CPU utilization and low-level metrics show similar trends. These results were captured using the scripts on github [7] to illustrate how this approach compares with other pre-existing mechanisms. This data is not to be interpreted as scientific data captured in a fully isolated lab setting, but instead as best effort, illustrative information comparing and contrasting tradeoffs. The absolute QPS results are higher than our previous submission, but the relative differences between variants are equivalent. Because the patches have been rebased on 6.12, several factors have likely influenced the overall performance. Most importantly, we had to switch to a new set of basic kernel options, which has likely altered the baseline performance. Because the overall comparison of variants still holds, we have not attempted to recreate the exact set of kernel options from the previous submission. Compare: - Throughput (MAX) and latencies of base vs suspend. - CPU usage of napibusy and fullbusy during lower load (200K, 400K for example) vs suspend. - Latency of the defer variants vs suspend as timeout and load increases. The overall takeaway is that the suspend variants provide a superior combination of high throughput, low latency, and low cpu utilization compared to all other variants. Each of the suspend variants works very well, but some fine-tuning between latency and cpu utilization is still possible by tuning the small timeout (gro_flush_timeout). Note: we've reorganized the results to make comparison among testcases with the same load easier. testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 200K 200024 127 254 458 25 12748 11289 defer10 200K 199991 64 128 166 27 18763 16574 defer20 200K 199986 72 135 178 25 15405 14173 defer50 200K 200025 91 149 198 23 12275 12203 defer200 200K 199996 182 266 326 18 8595 9183 fullbusy 200K 200040 58 123 167 100 43641 23145 napibusy 200K 200009 115 244 299 56 24797 24693 suspend10 200K 200005 63 128 167 32 19559 17240 suspend20 200K 199952 69 132 170 29 16324 14838 suspend50 200K 200019 84 144 189 26 13106 12516 suspend200 200K 199978 168 264 326 20 9331 9643 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 400K 400017 157 292 762 39 9287 9325 defer10 400K 400033 71 141 204 53 13950 12943 defer20 400K 399935 79 150 212 47 12027 11673 defer50 400K 399888 101 171 231 39 9556 9921 defer200 400K 399993 200 287 358 32 7428 8576 fullbusy 400K 400018 63 132 203 100 21827 16062 napibusy 400K 399970 89 230 292 83 18156 16508 suspend10 400K 400061 69 139 202 54 13576 13057 suspend20 400K 399988 73 144 206 49 11930 11773 suspend50 400K 399975 88 161 218 42 9996 10270 suspend200 400K 399954 172 276 353 34 7847 8713 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 600K 600031 166 289 631 61 9188 8787 defer10 600K 599967 85 167 262 75 11833 10947 defer20 600K 599888 89 165 243 66 10513 10362 defer50 600K 600072 109 185 253 55 8664 9190 defer200 600K 599951 222 315 393 45 6892 8213 fullbusy 600K 600041 69 145 227 100 14549 13936 napibusy 600K 599980 79 188 280 96 13927 14155 suspend10 600K 600028 78 159 267 69 10877 11032 suspend20 600K 600026 81 159 254 64 9922 10320 suspend50 600K 600007 96 178 258 57 8681 9331 suspend200 600K 599964 177 295 369 47 7115 8366 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 800K 800034 198 329 698 84 9366 8338 defer10 800K 799718 243 642 1457 95 10532 9007 defer20 800K 800009 132 245 399 89 9956 8979 defer50 800K 800024 136 228 378 80 9002 8598 defer200 800K 799965 255 362 473 66 7481 8147 fullbusy 800K 799927 78 157 253 100 10915 12533 napibusy 800K 799870 81 173 273 99 10826 12532 suspend10 800K 799991 84 167 269 83 9380 9802 suspend20 800K 799979 90 172 290 78 8765 9404 suspend50 800K 800031 106 191 307 71 7945 8805 suspend200 800K 799905 182 307 411 62 6985 8242 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base 1000K 919543 3805 6390 14229 98 9324 7978 defer10 1000K 850751 4574 7382 15370 99 10218 8470 defer20 1000K 890296 4736 6862 14858 99 9708 8277 defer50 1000K 932694 3463 6180 13251 97 9148 8053 defer200 1000K 951311 3524 6052 13599 96 8875 7845 fullbusy 1000K 1000011 90 181 278 100 8731 10686 napibusy 1000K 1000050 93 184 280 100 8721 10547 suspend10 1000K 999962 101 193 306 92 8138 8980 suspend20 1000K 1000030 103 191 324 88 7844 8763 suspend50 1000K 1000001 114 202 320 83 7396 8431 suspend200 1000K 999965 185 314 428 76 6733 8072 testcase load qps avglat 95%lat 99%lat cpu cpq ipq base MAX 1005592 4651 6594 14979 100 8679 7918 defer10 MAX 928204 5106 7286 15199 100 9398 8380 defer20 MAX 984663 4774 6518 14920 100 8861 8063 defer50 MAX 1044099 4431 6368 14652 100 8350 7948 defer200 MAX 1040451 4423 6610 14674 100 8380 7931 fullbusy MAX 1236608 3715 3987 12805 100 7051 7936 napibusy MAX 1077516 4345 10155 15957 100 8080 7842 suspend10 MAX 1218344 3760 3990 12585 100 7150 7935 suspend20 MAX 1220056 3752 4053 12602 100 7150 7961 suspend50 MAX 1213666 3791 4103 12919 100 7183 7959 suspend200 MAX 1217411 3768 3988 12863 100 7161 7954 ~ FAQ - Can the new timeout value be threaded through the new epoll ioctl ? Only with difficulty. The epoll ioctl sets options on an epoll context and the NAPI ID associated with an epoll context can change based on what file descriptors a user app adds to the epoll context. This would introduce complexity in the API from the user perspective and also complexity in the kernel. - Can irq suspend be built by combining NIC coalescing and gro_flush_timeout ? No. The problem is that the long timeout must engage if and only if prefer-busy is active. When using NIC coalescing for the short timeout (without napi_defer_hard_irqs/gro_flush_timeout), an interrupt after an idle period will trigger softirq, which will run napi polling. At this point, prefer-busy is not active, so NIC interrupts would be re-enabled. Then it is not possible for the longer timeout to interject to switch control back to polling. In other words, only by using the software timer for the short timeout, it is possible to extend the timeout without having to reprogram the NIC timer or reach down directly and disable interrupts. Using gro_flush_timeout for the long timeout also has problems, for the same underlying reason. In the current napi implementation, gro_flush_timeout is not tied to prefer-busy. We'd either have to change that and in the process modify the existing deferral mechanism, or introduce a state variable to determine whether gro_flush_timeout is used as long timeout for irq suspend or whether it is used for its default purpose. In an earlier version, we did try something similar to the latter and made it work, but it ends up being a lot more convoluted than our current proposal. - Isn't it already possible to combine busy looping with irq deferral? Yes, in fact enabling irq deferral via napi_defer_hard_irqs and gro_flush_timeout is a precondition for prefer_busy_poll to have an effect. If the application also uses a tight busy loop with essentially nonblocking epoll_wait (accomplished with a very short timeout parameter), this is the fullbusy case shown in the results. An application using blocking epoll_wait is shown as the napibusy case in the result. It's a hybrid approach that provides limited latency benefits compared to the base case and plain irq deferral, but not as good as fullbusy or suspend. ~ Special thanks Several people were involved in earlier stages of the development of this mechanism whom we'd like to thank: - Peter Cai (CC'd), for the initial kernel patch and his contributions to the paper. - Mohammadamin Shafie (CC'd), for testing various versions of the kernel patch and providing helpful feedback. Thanks, Martin and Joe [1]: https://lore.kernel.org/netdev/20240812125717.413108-1-jdamato@fastly.com/ [2]: https://doi.org/10.1145/3626780 [3]: https://github.com/memcached/memcached/blob/master/doc/napi_ids.txt [4]: https://github.com/leverich/mutilate [5]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/mem… [6]: https://raw.githubusercontent.com/martinkarsten/irqsuspend/main/patches/lib… [7]: https://github.com/martinkarsten/irqsuspend [8]: https://github.com/martinkarsten/irqsuspend/tree/main/results v3: - Added Stanislav Fomichev's Acked-by to every patch except the newly added selftest. - Added Bagas Sanjaya's Reviewed-by to the documentation patch. - Fixed the commit message of patch 2 to remove a reference to the now non-existent sysfs setting. - Added a self test which tests both "regular" busy poll and busy poll with suspend enabled. This was added as patch 6 as requested by Paolo. netdevsim was chosen instead of veth due to netdevsim's pre-existing support for netdev-genl. See the commit message of patch 6 for more details. v2: https://lore.kernel.org/bpf/20241021015311.95468-1-jdamato@fastly.com/ - Cover letter updated, including a re-run of test data. - Patch 1 rewritten to use netdev-genl instead of sysfs. - Patch 3 updated with a comment added to napi_resume_irqs. - Patch 4 rebased to apply now that commit b9ca079dd6b0 ("eventpoll: Annotate data-race of busy_poll_usecs") has been picked up from VFS. - Patch 6 updated the kernel documentation. rfc -> v1: - Cover letter updated to include more details. - Patch 1 updated to remove the documentation added. This was moved to patch 6 with the rest of the docs (see below). - Patch 5 updated to fix an error uncovered by the kernel build robot. See patch 5's changelog for more details. - Patch 6 added which updates kernel documentation. Joe Damato (2): selftests: net: Add busy_poll_test docs: networking: Describe irq suspension Martin Karsten (5): net: Add napi_struct parameter irq_suspend_timeout net: Suspend softirq when prefer_busy_poll is set net: Add control functions for irq suspension eventpoll: Trigger napi_busy_loop, if prefer_busy_poll is set eventpoll: Control irq suspension for prefer_busy_poll Documentation/netlink/specs/netdev.yaml | 7 + Documentation/networking/napi.rst | 132 +++++++++- fs/eventpoll.c | 35 ++- include/linux/netdevice.h | 2 + include/net/busy_poll.h | 3 + include/uapi/linux/netdev.h | 1 + net/core/dev.c | 58 ++++- net/core/dev.h | 25 ++ net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 12 + tools/include/uapi/linux/netdev.h | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 + tools/testing/selftests/net/busy_poll_test.sh | 164 ++++++++++++ tools/testing/selftests/net/busy_poller.c | 245 ++++++++++++++++++ 15 files changed, 683 insertions(+), 10 deletions(-) create mode 100755 tools/testing/selftests/net/busy_poll_test.sh create mode 100644 tools/testing/selftests/net/busy_poller.c base-commit: 9e114ec8084020e10e1cb7b43dbbf6e69940866b -- 2.25.1

1 year, 1 month

2
3
0 0

[PATCH] kselftest/arm64: Use ksft_perror() to log MTE failures

by Mark Brown

The logging in the allocation helpers variously uses ksft_print_msg() with very intermittent logging of errno and perror() (which won't produce KTAP conformant output) when logging the result of API calls that set errno. Standardise on using the ksft_perror() helper in these cases so that more information is available should the tests fail. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/mte/mte_common_util.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c index 00ffd34c66d301ee7d5c99e6b8d9d5d944520b7f..46958b58801e90ceb79be76f57c7f72b50d43b3c 100644 --- a/tools/testing/selftests/arm64/mte/mte_common_util.c +++ b/tools/testing/selftests/arm64/mte/mte_common_util.c @@ -150,13 +150,13 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping, map_flag |= MAP_PRIVATE; ptr = mmap(NULL, entire_size, prot_flag, map_flag, fd, 0); if (ptr == MAP_FAILED) { - ksft_print_msg("FAIL: mmap allocation\n"); + ksft_perror("mmap()"); return NULL; } if (mem_type == USE_MPROTECT) { if (mprotect(ptr, entire_size, prot_flag | PROT_MTE)) { + ksft_perror("mprotect(PROT_MTE)"); munmap(ptr, size); - ksft_print_msg("FAIL: mprotect PROT_MTE property\n"); return NULL; } } @@ -190,13 +190,13 @@ void *mte_allocate_file_memory(size_t size, int mem_type, int mapping, bool tags lseek(fd, 0, SEEK_SET); for (index = INIT_BUFFER_SIZE; index < size; index += INIT_BUFFER_SIZE) { if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) { - perror("initialising buffer"); + ksft_perror("initialising buffer"); return NULL; } } index -= INIT_BUFFER_SIZE; if (write(fd, buffer, size - index) != size - index) { - perror("initialising buffer"); + ksft_perror("initialising buffer"); return NULL; } return __mte_allocate_memory_range(size, mem_type, mapping, 0, 0, tags, fd); @@ -217,12 +217,12 @@ void *mte_allocate_file_memory_tag_range(size_t size, int mem_type, int mapping, lseek(fd, 0, SEEK_SET); for (index = INIT_BUFFER_SIZE; index < map_size; index += INIT_BUFFER_SIZE) if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) { - perror("initialising buffer"); + ksft_perror("initialising buffer"); return NULL; } index -= INIT_BUFFER_SIZE; if (write(fd, buffer, map_size - index) != map_size - index) { - perror("initialising buffer"); + ksft_perror("initialising buffer"); return NULL; } return __mte_allocate_memory_range(size, mem_type, mapping, range_before, @@ -359,7 +359,7 @@ int create_temp_file(void) /* Create a file in the tmpfs filesystem */ fd = mkstemp(&filename[0]); if (fd == -1) { - perror(filename); + ksft_perror(filename); ksft_print_msg("FAIL: Unable to open temporary file\n"); return 0; } --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241028-arm64-mte-test-logging-6c6e737b1c62 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

3
2
0 0

[PATCH] kselftest/arm64: Fix encoding for SVE B16B16 test

by Mark Brown

The test for SVE_B16B16 had a cut'n'paste of a SME instruction, fix it with a relevant SVE instruction. Fixes: 44d10c27bd75 ("kselftest/arm64: Add 2023 DPISA hwcap test coverage") Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/abi/hwcap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index f2d6007a2b983eba77a880ec7e614396a6cb1377..1e4ed89802f76c2bcbe4bfd1a9a987970db8b97d 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -361,8 +361,8 @@ static void sveaes_sigill(void) static void sveb16b16_sigill(void) { - /* BFADD ZA.H[W0, 0], {Z0.H-Z1.H} */ - asm volatile(".inst 0xC1E41C00" : : : ); + /* BFADD Z0.H, Z0.H, Z0.H */ + asm volatile(".inst 0x65000000" : : : ); } static void svepmull_sigill(void) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241024-arm64-b16b16-test-a1c7bad2478e Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

2
1
0 0

[PATCH RFC v2 0/5] Verify bias functionality for pinctrl_paris driver through new gpio test

by Nícolas F. R. A. Prado

This series was motivated by the regression fixed by 166bf8af9122 ("pinctrl: mediatek: common-v2: Fix broken bias-disable for PULL_PU_PD_RSEL_TYPE"). A bug was introduced in the pinctrl_paris driver which prevented certain pins from having their bias configured. Running this test on the mt8195-tomato platform with the test plan included below[1] shows the test passing with the fix applied, but failing without the fix: With fix: $ ./gpio-setget-config.py TAP version 13 # Using test plan file: ./google,tomato.yaml 1..3 ok 1 pinctrl_paris.34.pull-up ok 2 pinctrl_paris.34.pull-down ok 3 pinctrl_paris.34.disabled # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0 Without fix: $ ./gpio-setget-config.py TAP version 13 # Using test plan file: ./google,tomato.yaml 1..3 # Bias doesn't match: Expected pull-up, read pull-down. not ok 1 pinctrl_paris.34.pull-up ok 2 pinctrl_paris.34.pull-down # Bias doesn't match: Expected disabled, read pull-down. not ok 3 pinctrl_paris.34.disabled # Totals: pass:1 fail:2 xfail:0 xpass:0 skip:0 error:0 In order to achieve this, the first three patches expose bias configuration through the GPIO API in the MediaTek pinctrl drivers, notably, pinctrl_paris, patch 4 extends the gpio-mockup-cdev utility for use by patch 5, and patch 5 introduces a new GPIO kselftest that takes a test plan in YAML, which can be tailored per-platform to specify the configurations to test, and sets and gets back each pin configuration to verify that they match and thus that the driver is behaving as expected. Since the GPIO uAPI only allows setting the pin configuration, getting it back is done through pinconf-pins in the pinctrl debugfs folder. The test currently only verifies bias but it would be easy to extend to verify other pin configurations. The test plan YAML file can be customized for each use-case and is platform-dependant. For that reason, only an example is included in patch 3 and the user is supposed to provide their test plan. That said, the aim is to collect test plans for ease of use at [2]. [1] This is the test plan used for mt8195-tomato: - label: "pinctrl_paris" tests: # Pin 34 has type MTK_PULL_PU_PD_RSEL_TYPE and is unused. # Setting bias to MTK_PULL_PU_PD_RSEL_TYPE pins was fixed by # 166bf8af9122 ("pinctrl: mediatek: common-v2: Fix broken bias-disable for PULL_PU_PD_RSEL_TYPE") - pin: 34 bias: "pull-up" - pin: 34 bias: "pull-down" - pin: 34 bias: "disabled" [2] https://github.com/kernelci/platform-test-parameters Signed-off-by: Nícolas F. R. A. Prado <nfraprado(a)collabora.com> --- Changes in v2: - Added patches 2 and 3 enabling the extra GPIO pin configurations on the other mediatek drivers: pinctrl-moore and pinctrl-mtk-common - Tweaked function name in patch 1: mtk_pinconf_set -> mtk_paris_pin_config_set, to make it clear it is not a pinconf_ops - Adjusted commit message to make it clear the current support is limited to pins supported by the EINT controller - Link to v1: https://lore.kernel.org/r/20240909-kselftest-gpio-set-get-config-v1-0-16a06… --- Nícolas F. R. A. Prado (5): pinctrl: mediatek: paris: Expose more configurations to GPIO set_config pinctrl: mediatek: moore: Expose more configurations to GPIO set_config pinctrl: mediatek: common: Expose more configurations to GPIO set_config selftest: gpio: Add wait flag to gpio-mockup-cdev selftest: gpio: Add a new set-get config test drivers/pinctrl/mediatek/pinctrl-moore.c | 283 +++++++++++---------- drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 48 ++-- drivers/pinctrl/mediatek/pinctrl-paris.c | 26 +- tools/testing/selftests/gpio/Makefile | 2 +- tools/testing/selftests/gpio/gpio-mockup-cdev.c | 14 +- .../gpio-set-get-config-example-test-plan.yaml | 15 ++ .../testing/selftests/gpio/gpio-set-get-config.py | 183 +++++++++++++ 7 files changed, 395 insertions(+), 176 deletions(-) --- base-commit: a39230ecf6b3057f5897bc4744a790070cfbe7a8 change-id: 20240906-kselftest-gpio-set-get-config-6e5bb670c1a5 Best regards, -- Nícolas F. R. A. Prado <nfraprado(a)collabora.com>

1 year, 1 month

3
12
0 0

[PATCH v4] net: ipv4: Cache pmtu for all packet paths if multipath enabled

by Vladimir Vdovin

Check number of paths by fib_info_num_path(), and update_or_create_fnhe() for every path. Problem is that pmtu is cached only for the oif that has received icmp message "need to frag", other oifs will still try to use "default" iface mtu. V4: - fix selftest, do route lookup before checking cached exceptions V3: - added selftest - fixed compile error V2: - fix fib_info_num_path parameter pass An example topology showing the problem: | host1 +---------+ | dummy0 | 10.179.20.18/32 mtu9000 +---------+ +-----------+----------------+ +---------+ +---------+ | ens17f0 | 10.179.2.141/31 | ens17f1 | 10.179.2.13/31 +---------+ +---------+ | (all here have mtu 9000) | +------+ +------+ | ro1 | 10.179.2.140/31 | ro2 | 10.179.2.12/31 +------+ +------+ | | ---------+------------+-------------------+------ | +-----+ | ro3 | 10.10.10.10 mtu1500 +-----+ | ======================================== some networks ======================================== | +-----+ | eth0| 10.10.30.30 mtu9000 +-----+ | host2 host1 have enabled multipath and sysctl net.ipv4.fib_multipath_hash_policy = 1: default proto static src 10.179.20.18 nexthop via 10.179.2.12 dev ens17f1 weight 1 nexthop via 10.179.2.140 dev ens17f0 weight 1 When host1 tries to do pmtud from 10.179.20.18/32 to host2, host1 receives at ens17f1 iface an icmp packet from ro3 that ro3 mtu=1500. And host1 caches it in nexthop exceptions cache. Problem is that it is cached only for the iface that has received icmp, and there is no way that ro3 will send icmp msg to host1 via another path. Host1 now have this routes to host2: ip r g 10.10.30.30 sport 30000 dport 443 10.10.30.30 via 10.179.2.12 dev ens17f1 src 10.179.20.18 uid 0 cache expires 521sec mtu 1500 ip r g 10.10.30.30 sport 30033 dport 443 10.10.30.30 via 10.179.2.140 dev ens17f0 src 10.179.20.18 uid 0 cache So when host1 tries again to reach host2 with mtu>1500, if packet flow is lucky enough to be hashed with oif=ens17f1 its ok, if oif=ens17f0 it blackholes and still gets icmp msgs from ro3 to ens17f1, until lucky day when ro3 will send it through another flow to ens17f0. Signed-off-by: Vladimir Vdovin <deliran(a)verdict.gg> --- net/ipv4/route.c | 13 +++++ tools/testing/selftests/net/pmtu.sh | 79 ++++++++++++++++++++++++++++- 2 files changed, 91 insertions(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 723ac9181558..41162b5cc4cb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..f7ced4c436fb 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -266,7 +266,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 0" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -2329,6 +2330,82 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing || return $ksft_skip + + ip nexthop ls >/dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "Nexthop objects not supported; skipping tests" + exit $ksft_skip + fi + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + dummy0_a="192.168.99.99" + dummy0_b="192.168.88.88" + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + fail=0 + + #Set up host A with multipath routes to host B dummy0_b + run_cmd ${ns_a} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_a} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_a} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_a} ip link set dummy0 up + run_cmd ${ns_a} ip addr add ${dummy0_a} dev dummy0 + run_cmd ${ns_a} ip nexthop add id 201 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 202 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 203 group 201/202 + run_cmd ${ns_a} ip route add ${dummy0_b} nhid 203 + + #Set up host B with multipath routes to host A dummy0_a + run_cmd ${ns_b} sysctl -q net.ipv4.fib_multipath_hash_policy=1 + run_cmd ${ns_b} sysctl -q net.ipv4.ip_forward=1 + run_cmd ${ns_b} ip link add dummy0 mtu 2000 type dummy + run_cmd ${ns_b} ip link set dummy0 up + run_cmd ${ns_b} ip addr add ${dummy0_b} dev dummy0 + run_cmd ${ns_b} ip nexthop add id 201 via ${prefix4}.${b_r1}.2 dev veth_A-R1 + run_cmd ${ns_b} ip nexthop add id 202 via ${prefix4}.${b_r2}.2 dev veth_A-R2 + run_cmd ${ns_b} ip nexthop add id 203 group 201/202 + run_cmd ${ns_b} ip route add ${dummy0_a} nhid 203 + + #Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${dummy0_a} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_a} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${dummy0_b} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${dummy0_b} via ${prefix4}.${b_r2}.1 + + + #Ping and expect two nexthop exceptions for two routes in nh group + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dummy0_b}" + + #Do route lookup before checking cached exceptions + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R1 + run_cmd ${ns_a} ip route get ${dummy0_b} oif veth_A-R2 + + #Check cached exceptions + echo "$(ip -oneline route list cache)" + if [ "$(${ns_a} ip -oneline route list cache| grep mtu | wc -l)" -ne 2 ]; then + err " there are not enough cached exceptions" + fail=1 + fi + + return ${fail} +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." base-commit: 66600fac7a984dea4ae095411f644770b2561ede -- 2.43.5

1 year, 1 month

1
0
0 0

[PATCH v3 0/3] rust: kunit: Support KUnit tests with a user-space like syntax

by David Gow

This series was originally written by José Expósito, and has been modified and updated by Matt Gilbride and myself. The original version can be found here: https://github.com/Rust-for-Linux/linux/pull/950 Add support for writing KUnit tests in Rust. While Rust doctests are already converted to KUnit tests and run, they're really better suited for examples, rather than as first-class unit tests. This series implements a series of direct Rust bindings for KUnit tests, as well as a new macro which allows KUnit tests to be written using a close variant of normal Rust unit test syntax. The only change required is replacing '#[cfg(test)]' with '#[kunit_tests(kunit_test_suite_name)]' An example test would look like: #[kunit_tests(rust_kernel_hid_driver)] mod tests { use super::*; use crate::{c_str, driver, hid, prelude::*}; use core::ptr; struct SimpleTestDriver; impl Driver for SimpleTestDriver { type Data = (); } #[test] fn rust_test_hid_driver_adapter() { let mut hid = bindings::hid_driver::default(); let name = c_str!("SimpleTestDriver"); static MODULE: ThisModule = unsafe { ThisModule::from_ptr(ptr::null_mut()) }; let res = unsafe { <hid::Adapter<SimpleTestDriver> as driver::DriverOps>::register(&mut hid, name, &MODULE) }; assert_eq!(res, Err(ENODEV)); // The mock returns -19 } } Please give this a go, and make sure I haven't broken it! There's almost certainly a lot of improvements which can be made -- and there's a fair case to be made for replacing some of this with generated C code which can use the C macros -- but this is hopefully an adequate implementation for now, and the interface can (with luck) remain the same even if the implementation changes. A few small notable missing features: - Attributes (like the speed of a test) are hardcoded to the default value. - Similarly, the module name attribute is hardcoded to NULL. In C, we use the KBUILD_MODNAME macro, but I couldn't find a way to use this from Rust which wasn't more ugly than just disabling it. - Assertions are not automatically rewritten to use KUnit assertions. --- Changes since v2: https://lore.kernel.org/linux-kselftest/20241029092422.2884505-1-davidgow@g… - Include missing rust/macros/kunit.rs file from v2. (Thanks Boqun!) - The kunit_unsafe_test_suite!() macro will truncate the name of the suite if it is too long. (Thanks Alice!) - The proc macro now emits an error if the suite name is too long. - We no longer needlessly use UnsafeCell<> in kunit_unsafe_test_suite!(). (Thanks Alice!) Changes since v1: https://lore.kernel.org/lkml/20230720-rustbind-v1-0-c80db349e3b5@google.com… - Rebase on top of the latest rust-next (commit 718c4069896c) - Make kunit_case a const fn, rather than a macro (Thanks Boqun) - As a result, the null terminator is now created with kernel::kunit::kunit_case_null() - Use the C kunit_get_current_test() function to implement in_kunit_test(), rather than re-implementing it (less efficiently) ourselves. Changes since the GitHub PR: - Rebased on top of kselftest/kunit - Add const_mut_refs feature This may conflict with https://lore.kernel.org/lkml/20230503090708.2524310-6-nmi@metaspace.dk/ - Add rust/macros/kunit.rs to the KUnit MAINTAINERS entry --- José Expósito (3): rust: kunit: add KUnit case and suite macros rust: macros: add macro to easily run KUnit tests rust: kunit: allow to know if we are in a test MAINTAINERS | 1 + rust/kernel/kunit.rs | 191 +++++++++++++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + rust/macros/kunit.rs | 153 ++++++++++++++++++++++++++++++++++ rust/macros/lib.rs | 29 +++++++ 5 files changed, 375 insertions(+) create mode 100644 rust/macros/kunit.rs -- 2.47.0.163.g1226f6d8fa-goog

1 year, 1 month

2
6
0 0

[PATCH net-next] selftests: netdevsim: add fib_notifications to Makefile

by Jakub Kicinski

Commit 19d36d2971e6 ("selftests: netdevsim: Add fib_notifications test") added the test but didn't include it in the Makefile. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: andrew+netdev(a)lunn.ch CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org CC: petrm(a)nvidia.com --- tools/testing/selftests/drivers/net/netdevsim/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index 5bace0b7fb57..cc08b220323f 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -8,6 +8,7 @@ TEST_PROGS = devlink.sh \ ethtool-pause.sh \ ethtool-ring.sh \ fib.sh \ + fib_notifications.sh \ hw_stats_l3.sh \ nexthop.sh \ peer.sh \ -- 2.47.0

1 year, 1 month

3
2
0 0

[PATCH v3] selftests/net: Fix ./ns-XXXXXX not cleanup

by Li Zhijian

``` readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" readonly BASE=`basename $STATS` ``` It could be a mistake to write to $BASE rather than $STATS, where $STATS is used to save the NSTAT_HISTORY and it will be cleaned up before exit. Although since we've been creating the wrong file this whole time and everything worked, it's fine to remove these 2 lines completely 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> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- Cc: netdev(a)vger.kernel.org --- V3: Remove these 2 lines rather than fixing the filename --- Hello, Cover letter is here. This patch set aims to make 'git status' clear after 'make' and 'make run_tests' for kselftests. --- V2: nothing change Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- tools/testing/selftests/net/veth.sh | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 4f1edbafb946..6bb7dfaa30b6 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -46,8 +46,6 @@ create_ns() { ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24 ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad done - echo "#kernel" > $BASE - chmod go-rw $BASE } __chk_flag() { -- 2.44.0

1 year, 1 month

2
1
0 0

[PATCH net-next v8 00/24] Introducing OpenVPN Data Channel Offload

by Antonio Quartulli

This is the 8th version of the ovpn patchset. Thanks Sergey for arguing regarding splitting PEER_SET into SET and NEW. I decided to follow this suggestion as it makes the API and its return value easier to work with. Thanks Donald for the suggestions regarding the NL API - they have all been implemented (unless I forgot some, but hopefully I did not). Notable changes from v7: * Netlink API adjustments: ** renamed NL API from OP_OBJ to OBJ_OP (i.e. from SET_PEER to PEER_SET) ** split PEER_SET from PEER_NEW for better clarity in case of error ** renamed NL API from NEW/DEL_IFACE to DEV_NEW/DEL ** converted all underscores to dashes in YML NL spec ** split sockaddr_remote attr into ipv4/6, port and v6_scope_id attrs ** split local_ip attr into local_ipv4 and local_ipv6 attrs ** turned keyconf into a root attribute (it was nested in peer before) ** made key_swap use a keyconf object rather than a peer for consistency with key mgmt API ** created specific op for peer_del notification (peer_del_ntf) ** created specific op for key_swap notification (key_swap_ntf) ** allow user to update VPN IPv4/6 (peer is now rehashable) ** converted port attrs from u32 to u16 for better consistency with userspace code * added rtnl_ops .dellink implementation * removed patch 2 as it's not needed anymore thanks to the point above * moved rtnl_ops .kind initialization to first patch * updated MAINTAINERS file with Github tree and selftest folder * wrapped long lines in selftest scripts BONUS: used b4 for the first time to prepare the patchset and send it Please note that patches previously reviewed by Andrew Lunn have retained the Reviewed-by tag as they have been simply rebased without any modification. The latest code can also be found at: https://github.com/OpenVPN/linux-kernel-ovpn Thanks a lot! Best Regards, Antonio Quartulli OpenVPN Inc. --- Antonio Quartulli (24): netlink: add NLA_POLICY_MAX_LEN macro net: introduce OpenVPN Data Channel Offload (ovpn) ovpn: add basic netlink support ovpn: add basic interface creation/destruction/management routines ovpn: implement interface creation/destruction via netlink ovpn: keep carrier always on ovpn: introduce the ovpn_peer object ovpn: introduce the ovpn_socket object ovpn: implement basic TX path (UDP) ovpn: implement basic RX path (UDP) ovpn: implement packet processing ovpn: store tunnel and transport statistics ovpn: implement TCP transport ovpn: implement multi-peer support ovpn: implement peer lookup logic ovpn: implement keepalive mechanism ovpn: add support for updating local UDP endpoint ovpn: add support for peer floating ovpn: implement peer add/dump/delete via netlink ovpn: implement key add/del/swap via netlink ovpn: kill key and notify userspace in case of IV exhaustion ovpn: notify userspace when a peer is deleted ovpn: add basic ethtool support testing/selftest: add test tool and scripts for ovpn module Documentation/netlink/specs/ovpn.yaml | 387 +++++ MAINTAINERS | 11 + drivers/net/Kconfig | 15 + drivers/net/Makefile | 1 + drivers/net/ovpn/Makefile | 22 + drivers/net/ovpn/bind.c | 54 + drivers/net/ovpn/bind.h | 117 ++ drivers/net/ovpn/crypto.c | 172 ++ drivers/net/ovpn/crypto.h | 138 ++ drivers/net/ovpn/crypto_aead.c | 356 ++++ drivers/net/ovpn/crypto_aead.h | 31 + drivers/net/ovpn/io.c | 459 ++++++ drivers/net/ovpn/io.h | 25 + drivers/net/ovpn/main.c | 363 ++++ drivers/net/ovpn/main.h | 29 + drivers/net/ovpn/netlink-gen.c | 224 +++ drivers/net/ovpn/netlink-gen.h | 42 + drivers/net/ovpn/netlink.c | 1099 +++++++++++++ drivers/net/ovpn/netlink.h | 18 + drivers/net/ovpn/ovpnstruct.h | 60 + drivers/net/ovpn/packet.h | 40 + drivers/net/ovpn/peer.c | 1207 ++++++++++++++ drivers/net/ovpn/peer.h | 172 ++ drivers/net/ovpn/pktid.c | 130 ++ drivers/net/ovpn/pktid.h | 87 + drivers/net/ovpn/proto.h | 104 ++ drivers/net/ovpn/skb.h | 61 + drivers/net/ovpn/socket.c | 165 ++ drivers/net/ovpn/socket.h | 53 + drivers/net/ovpn/stats.c | 21 + drivers/net/ovpn/stats.h | 47 + drivers/net/ovpn/tcp.c | 506 ++++++ drivers/net/ovpn/tcp.h | 43 + drivers/net/ovpn/udp.c | 406 +++++ drivers/net/ovpn/udp.h | 26 + include/net/netlink.h | 1 + include/uapi/linux/ovpn.h | 116 ++ include/uapi/linux/udp.h | 1 + tools/net/ynl/ynl-gen-c.py | 2 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/ovpn/.gitignore | 2 + tools/testing/selftests/net/ovpn/Makefile | 18 + tools/testing/selftests/net/ovpn/config | 8 + tools/testing/selftests/net/ovpn/data-test-tcp.sh | 9 + tools/testing/selftests/net/ovpn/data-test.sh | 153 ++ tools/testing/selftests/net/ovpn/data64.key | 5 + tools/testing/selftests/net/ovpn/float-test.sh | 118 ++ tools/testing/selftests/net/ovpn/ovpn-cli.c | 1822 +++++++++++++++++++++ tools/testing/selftests/net/ovpn/tcp_peers.txt | 5 + tools/testing/selftests/net/ovpn/udp_peers.txt | 5 + 50 files changed, 8957 insertions(+) --- base-commit: 44badc908f2c85711cb18e45e13119c10ad3a05f change-id: 20241002-b4-ovpn-eeee35c694a2 Best regards, -- Antonio Quartulli <antonio(a)openvpn.net>

1 year, 1 month

7
44
0 0

[PATCH -next] KVM: selftests: Use ARRAY_SIZE for array length

by Jiapeng Chong

Use of macro ARRAY_SIZE to calculate array size minimizes the redundant code and improves code reusability. ./tools/testing/selftests/kvm/x86_64/debug_regs.c:169:32-33: WARNING: Use ARRAY_SIZE. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=10847 Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/kvm/x86_64/debug_regs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 76cc2df9238a..2d814c1d1dc4 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -166,7 +166,7 @@ int main(void) /* Test single step */ target_rip = CAST_TO_RIP(ss_start); target_dr6 = 0xffff4ff0ULL; - for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) { + for (i = 0; i < ARRAY_SIZE(ss_size); i++) { target_rip += ss_size[i]; memset(&debug, 0, sizeof(debug)); debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP | -- 2.32.0.3.g01195cf9f

1 year, 1 month

2
1
0 0

[PATCH] hardware_disable_test: remove unused macro

by Ba Jing

The macro GUEST_CODE_PIO_PORT is never referenced in the code, just remove it. Signed-off-by: Ba Jing <bajing(a)cmss.chinamobile.com> --- tools/testing/selftests/kvm/hardware_disable_test.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index bce73bcb973c..94bd6ed24cf3 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -20,7 +20,6 @@ #define SLEEPING_THREAD_NUM (1 << 4) #define FORK_NUM (1ULL << 9) #define DELAY_US_MAX 2000 -#define GUEST_CODE_PIO_PORT 4 sem_t *sem; -- 2.33.0

1 year, 1 month

2
1
0 0

[PATCH net-next v6 00/12] selftests: ncdevmem: Add ncdevmem to ksft

by Stanislav Fomichev

The goal of the series is to simplify and make it possible to use ncdevmem in an automated way from the ksft python wrapper. ncdevmem is slowly mutated into a state where it uses stdout to print the payload and the python wrapper is added to make sure the arrived payload matches the expected one. v6: - fix compilation issue in 'Unify error handling' patch (Jakub) v5: - properly handle errors from inet_pton() and socket() (Paolo) - remove unneeded import from python selftest (Paolo) v4: - keep usage example with validation (Mina) - fix compilation issue in one patch (s/start_queues/start_queue/) v3: - keep and refine the comment about ncdevmem invocation (Mina) - add the comment about not enforcing exit status for ntuple reset (Mina) - make configure_headersplit more robust (Mina) - use num_queues/2 in selftest and let the users override it (Mina) - remove memory_provider.memcpy_to_device (Mina) - keep ksft as is (don't use -v validate flags): we are gonna need a --debug-disable flag to make it less chatty; otherwise it times out when sending too much data; so leaving it as a separate follow up v2: - don't remove validation (Mina) - keep 5-tuple flow steering but use it only when -c is provided (Mina) - remove separate flag for probing (Mina) - move ncdevmem under drivers/net/hw, not drivers/net (Jakub) Cc: Mina Almasry <almasrymina(a)google.com> Stanislav Fomichev (12): selftests: ncdevmem: Redirect all non-payload output to stderr selftests: ncdevmem: Separate out dmabuf provider selftests: ncdevmem: Unify error handling selftests: ncdevmem: Make client_ip optional selftests: ncdevmem: Remove default arguments selftests: ncdevmem: Switch to AF_INET6 selftests: ncdevmem: Properly reset flow steering selftests: ncdevmem: Use YNL to enable TCP header split selftests: ncdevmem: Remove hard-coded queue numbers selftests: ncdevmem: Run selftest when none of the -s or -c has been provided selftests: ncdevmem: Move ncdevmem under drivers/net/hw selftests: ncdevmem: Add automated test .../selftests/drivers/net/hw/.gitignore | 1 + .../testing/selftests/drivers/net/hw/Makefile | 9 + .../selftests/drivers/net/hw/devmem.py | 45 + .../selftests/drivers/net/hw/ncdevmem.c | 773 ++++++++++++++++++ tools/testing/selftests/net/.gitignore | 1 - tools/testing/selftests/net/Makefile | 8 - tools/testing/selftests/net/ncdevmem.c | 570 ------------- 7 files changed, 828 insertions(+), 579 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/.gitignore create mode 100755 tools/testing/selftests/drivers/net/hw/devmem.py create mode 100644 tools/testing/selftests/drivers/net/hw/ncdevmem.c delete mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.47.0

1 year, 1 month

3
19
0 0

[PATCH v2 0/9] arm64: Support 2024 dpISA extensions

by Mark Brown

The 2024 architecture release includes a number of data processing extensions, mostly SVE and SME additions with a few others. These are all very straightforward extensions which add instructions but no architectural state so only need hwcaps and exposing of the ID registers to KVM guests and userspace. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Filter KVM guest visible bitfields in ID_AA64ISAR3_EL1 to only those we make writeable. - Link to v1: https://lore.kernel.org/r/20241028-arm64-2024-dpisa-v1-0-a38d08b008a8@kerne… --- Mark Brown (9): arm64/sysreg: Update ID_AA64PFR2_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR3_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64FPFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ZFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64SMFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR2_EL1 to DDI0601 2024-09 arm64/hwcap: Describe 2024 dpISA extensions to userspace KVM: arm64: Allow control of dpISA extensions in ID_AA64ISAR3_EL1 kselftest/arm64: Add 2024 dpISA extensions to hwcap test Documentation/arch/arm64/elf_hwcaps.rst | 51 ++++++ arch/arm64/include/asm/hwcap.h | 17 ++ arch/arm64/include/uapi/asm/hwcap.h | 17 ++ arch/arm64/kernel/cpufeature.c | 35 ++++ arch/arm64/kernel/cpuinfo.c | 17 ++ arch/arm64/kvm/sys_regs.c | 6 +- arch/arm64/tools/sysreg | 87 +++++++++- tools/testing/selftests/arm64/abi/hwcap.c | 273 +++++++++++++++++++++++++++++- 8 files changed, 493 insertions(+), 10 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241008-arm64-2024-dpisa-8091074a7f48 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

2
10
0 0

[PATCH v4 0/3] bpf: Using binary search to improve the performance of btf_find_by_name_kind

by Donglin Peng

Currently, we are only using the linear search method to find the type id by the name, which has a time complexity of O(n). This change involves sorting the names of btf types in ascending order and using binary search, which has a time complexity of O(log(n)). This idea was inspired by the following patch: 60443c88f3a8 ("kallsyms: Improve the performance of kallsyms_lookup_name()"). At present, this improvement is only for searching in vmlinux's and module's BTFs. Another change is the search direction, where we search the BTF first and then its base, the type id of the first matched btf_type will be returned. Here is a time-consuming result that finding 87590 type ids by their names in vmlinux's BTF. Before: 158426 ms After: 114 ms The average lookup performance has improved more than 1000x in the above scenario. v4: - Divide the patch into two parts: kernel and libbpf - Use Eduard's code to sort btf_types in the btf__dedup function - Correct some btf testcases due to modifications of the order of btf_types. v3: - Link: https://lore.kernel.org/all/20240608140835.965949-1-dolinux.peng@gmail.com/ - Sort btf_types during build process other than during boot, to reduce the overhead of memory and boot time. v2: - Link: https://lore.kernel.org/all/20230909091646.420163-1-pengdonglin@sangfor.com… Donglin Peng (3): libbpf: Sort btf_types in ascending order by name bpf: Using binary search to improve the performance of btf_find_by_name_kind libbpf: Using binary search to improve the performance of btf__find_by_name_kind include/linux/btf.h | 1 + kernel/bpf/btf.c | 157 +++++++++- tools/lib/bpf/btf.c | 274 +++++++++++++--- tools/testing/selftests/bpf/prog_tests/btf.c | 296 +++++++++--------- .../bpf/prog_tests/btf_dedup_split.c | 64 ++-- 5 files changed, 555 insertions(+), 237 deletions(-) -- 2.34.1

1 year, 1 month

2
12
0 0

[PATCH v3 0/4] vfio-pci support pasid attach/detach

by Yi Liu

This adds the pasid attach/detach uAPIs for userspace to attach/detach a PASID of a device to/from a given ioas/hwpt. Only vfio-pci driver is enabled in this series. After this series, PASID-capable devices bound with vfio-pci can report PASID capability to userspace and VM to enable PASID usages like Shared Virtual Addressing (SVA). Based on the discussion about reporting the vPASID to VM [1], it's agreed that we will let the userspace VMM to synthesize the vPASID capability. The VMM needs to figure out a hole to put the vPASID cap. This includes the hidden bits handling for some devices. While, it's up to the userspace, it's not the focus of this series. This series first adds the helpers for pasid attach in vfio core and then adds the device cdev ioctls for pasid attach/detach. In the end of this series, the IOMMU_GET_HW_INFO ioctl is extended to report the PCI PASID capability to the userspace. Userspace should check this before using any PASID related uAPIs provided by VFIO, which is the agreement in [2]. This series depends on the iommufd pasid attach/detach series [3]. The completed code can be found at [4], tested with a hacky Qemu branch [5]. [1] https://lore.kernel.org/kvm/BN9PR11MB5276318969A212AD0649C7BE8CBE2@BN9PR11M… [2] https://lore.kernel.org/kvm/4f2daf50-a5ad-4599-ab59-bcfc008688d8@intel.com/ [3] https://lore.kernel.org/linux-iommu/20240912131255.13305-1-yi.l.liu@intel.c… [4] https://github.com/yiliu1765/iommufd/tree/iommufd_pasid [5] https://github.com/yiliu1765/qemu/tree/wip/zhenzhong/iommufd_nesting_rfcv2-… Change log: v3: - Misc enhancement on patch 01 of v2 (Alex, Jason) - Add Jason's r-b to patch 03 of v2 - Drop the logic that report PASID via VFIO_DEVICE_FEATURE ioctl - Extend IOMMU_GET_HW_INFO to report PASID support (Kevin, Jason, Alex) v2: https://lore.kernel.org/kvm/20240412082121.33382-1-yi.l.liu@intel.com/ - Use IDA to track if PASID is attached or not in VFIO. (Jason) - Fix the issue of calling pasid_at[de]tach_ioas callback unconditionally (Alex) - Fix the wrong data copy in vfio_df_ioctl_pasid_detach_pt() (Zhenzhong) - Minor tweaks in comments (Kevin) v1: https://lore.kernel.org/kvm/20231127063909.129153-1-yi.l.liu@intel.com/ - Report PASID capability via VFIO_DEVICE_FEATURE (Alex) rfc: https://lore.kernel.org/linux-iommu/20230926093121.18676-1-yi.l.liu@intel.c… Regards, Yi Liu Yi Liu (4): ida: Add ida_find_first_range() vfio-iommufd: Support pasid [at|de]tach for physical VFIO devices vfio: Add VFIO_DEVICE_PASID_[AT|DE]TACH_IOMMUFD_PT iommufd: Extend IOMMU_GET_HW_INFO to report PASID capability drivers/iommu/iommufd/device.c | 27 +++++++++++++- drivers/pci/ats.c | 32 ++++++++++++++++ drivers/vfio/device_cdev.c | 51 ++++++++++++++++++++++++++ drivers/vfio/iommufd.c | 50 +++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci.c | 2 + drivers/vfio/vfio.h | 4 ++ drivers/vfio/vfio_main.c | 8 ++++ include/linux/idr.h | 11 ++++++ include/linux/pci-ats.h | 3 ++ include/linux/vfio.h | 11 ++++++ include/uapi/linux/iommufd.h | 14 ++++++- include/uapi/linux/vfio.h | 55 ++++++++++++++++++++++++++++ lib/idr.c | 67 ++++++++++++++++++++++++++++++++++ 13 files changed, 333 insertions(+), 2 deletions(-) -- 2.34.1

1 year, 1 month

7
29
0 0

[PATCH net-next v6 0/3] Threads support in proc connector

by Anjali Kulkarni

Recently we committed a fix to allow processes to receive notifications for non-zero exits via the process connector module. Commit is a4c9a56e6a2c. However, for threads, when it does a pthread_exit(&exit_status) call, the kernel is not aware of the exit status with which pthread_exit is called. It is sent by child thread to the parent process, if it is waiting in pthread_join(). Hence, for a thread exiting abnormally, kernel cannot send notifications to any listening processes. The exception to this is if the thread is sent a signal which it has not handled, and dies along with it's process as a result; for eg. SIGSEGV or SIGKILL. In this case, kernel is aware of the non-zero exit and sends a notification for it. For our use case, we cannot have parent wait in pthread_join, one of the main reasons for this being that we do not want to track normal pthread_exit(), which could be a very large number. We only want to be notified of any abnormal exits. Hence, threads are created with pthread_attr_t set to PTHREAD_CREATE_DETACHED. To fix this problem, we add a new type PROC_CN_MCAST_NOTIFY to proc connector API, which allows a thread to send it's exit status to kernel either when it needs to call pthread_exit() with non-zero value to indicate some error or from signal handler before pthread_exit(). v5->v6 changes: - As suggested by Simon Horman, fixed style issues (some old) by running ./scripts/checkpatch.pl --strict --max-line-length=80 - Removed inline functions as suggested by Simon Horman - Added "depends on" in Kconfig.debug as suggested by Stanislav Fomichev - Removed warning while compilation with kernel space headers as suggested by Simon Horman - Removed "comm" field, will send separate patch for this. - Added kunit configs in tools/testing/kunit/configs/all_tests.config with it's dependencies. v4->v5 changes: - Handled comment by Stanislav Fomichev to fix a print format error. - Made thread.c completely automated by starting proc_filter program from within threads.c. - Changed name CONFIG_CN_HASH_KUNIT_TEST to CN_HASH_KUNIT_TEST in Kconfig.debug and changed display text. v3->v4 changes: - Reduce size of exit.log by removing unnecessary text. v2->v3 changes: - Handled comment by Liam Howlett to set hdev to NULL and add comment on it. - Handled comment by Liam Howlett to combine functions for deleting+get and deleting into one in cn_hash.c - Handled comment by Liam Howlett to remove extern in the functions defined in cn_hash_test.h - Some nits by Liam Howlett fixed. - Handled comment by Liam Howlett to make threads test automated. proc_filter.c creates exit.log, which is read by thread.c and checks the values reported. - Added "comm" field to struct proc_event, to copy the task's name to the packet to allow further filtering by packets. v1->v2 changes: - Handled comment by Peter Zijlstra to remove locking for PF_EXIT_NOTIFY task->flags. - Added error handling in thread.c v->v1 changes: - Handled comment by Simon Horman to remove unused err in cn_proc.c - Handled comment by Simon Horman to make adata and key_display static in cn_hash_test.c Anjali Kulkarni (3): connector/cn_proc: Add hash table for threads connector/cn_proc: Kunit tests for threads hash table connector/cn_proc: Selftest for threads drivers/connector/Makefile | 2 +- drivers/connector/cn_hash.c | 216 ++++++++++++++++ drivers/connector/cn_proc.c | 81 ++++-- drivers/connector/connector.c | 88 ++++++- include/linux/connector.h | 62 ++++- include/linux/sched.h | 2 +- include/uapi/linux/cn_proc.h | 4 +- lib/Kconfig.debug | 19 ++ lib/Makefile | 1 + lib/cn_hash_test.c | 169 +++++++++++++ lib/cn_hash_test.h | 10 + tools/testing/kunit/configs/all_tests.config | 5 + tools/testing/selftests/connector/Makefile | 25 ++ .../testing/selftests/connector/proc_filter.c | 63 +++-- tools/testing/selftests/connector/thread.c | 238 ++++++++++++++++++ .../selftests/connector/thread_filter.c | 96 +++++++ 16 files changed, 1027 insertions(+), 54 deletions(-) create mode 100644 drivers/connector/cn_hash.c create mode 100644 lib/cn_hash_test.c create mode 100644 lib/cn_hash_test.h create mode 100644 tools/testing/selftests/connector/thread.c create mode 100644 tools/testing/selftests/connector/thread_filter.c -- 2.46.0

1 year, 1 month

2
4
0 0

[PATCH RFT v11 0/8] fork: Support shadow stacks in clone3()

by Mark Brown

The kernel has recently added support for shadow stacks, currently x86 only using their CET feature but both arm64 and RISC-V have equivalent features (GCS and Zicfiss respectively), I am actively working on GCS[1]. With shadow stacks the hardware maintains an additional stack containing only the return addresses for branch instructions which is not generally writeable by userspace and ensures that any returns are to the recorded addresses. This provides some protection against ROP attacks and making it easier to collect call stacks. These shadow stacks are allocated in the address space of the userspace process. Our API for shadow stacks does not currently offer userspace any flexiblity for managing the allocation of shadow stacks for newly created threads, instead the kernel allocates a new shadow stack with the same size as the normal stack whenever a thread is created with the feature enabled. The stacks allocated in this way are freed by the kernel when the thread exits or shadow stacks are disabled for the thread. This lack of flexibility and control isn't ideal, in the vast majority of cases the shadow stack will be over allocated and the implicit allocation and deallocation is not consistent with other interfaces. As far as I can tell the interface is done in this manner mainly because the shadow stack patches were in development since before clone3() was implemented. Since clone3() is readily extensible let's add support for specifying a shadow stack when creating a new thread or process, keeping the current implicit allocation behaviour if one is not specified either with clone3() or through the use of clone(). The user must provide a shadow stack pointer, this must point to memory mapped for use as a shadow stackby map_shadow_stack() with an architecture specified shadow stack token at the top of the stack. Please note that the x86 portions of this code are build tested only, I don't appear to have a system that can run CET available to me. [1] https://lore.kernel.org/linux-arm-kernel/20241001-arm64-gcs-v13-0-222b78d87… Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v11: - Rebase onto arm64 for-next/gcs, which is based on v6.12-rc1, and integrate arm64 support. - Rework the interface to specify a shadow stack pointer rather than a base and size like we do for the regular stack. - Link to v10: https://lore.kernel.org/r/20240821-clone3-shadow-stack-v10-0-06e8797b9445@k… Changes in v10: - Integrate fixes & improvements for the x86 implementation from Rick Edgecombe. - Require that the shadow stack be VM_WRITE. - Require that the shadow stack base and size be sizeof(void *) aligned. - Clean up trailing newline. - Link to v9: https://lore.kernel.org/r/20240819-clone3-shadow-stack-v9-0-962d74f99464@ke… Changes in v9: - Pull token validation earlier and report problems with an error return to parent rather than signal delivery to the child. - Verify that the top of the supplied shadow stack is VM_SHADOW_STACK. - Rework token validation to only do the page mapping once. - Drop no longer needed support for testing for signals in selftest. - Fix typo in comments. - Link to v8: https://lore.kernel.org/r/20240808-clone3-shadow-stack-v8-0-0acf37caf14c@ke… Changes in v8: - Fix token verification with user specified shadow stack. - Don't track user managed shadow stacks for child processes. - Link to v7: https://lore.kernel.org/r/20240731-clone3-shadow-stack-v7-0-a9532eebfb1d@ke… Changes in v7: - Rebase onto v6.11-rc1. - Typo fixes. - Link to v6: https://lore.kernel.org/r/20240623-clone3-shadow-stack-v6-0-9ee7783b1fb9@ke… Changes in v6: - Rebase onto v6.10-rc3. - Ensure we don't try to free the parent shadow stack in error paths of x86 arch code. - Spelling fixes in userspace API document. - Additional cleanups and improvements to the clone3() tests to support the shadow stack tests. - Link to v5: https://lore.kernel.org/r/20240203-clone3-shadow-stack-v5-0-322c69598e4b@ke… Changes in v5: - Rebase onto v6.8-rc2. - Rework ABI to have the user allocate the shadow stack memory with map_shadow_stack() and a token. - Force inlining of the x86 shadow stack enablement. - Move shadow stack enablement out into a shared header for reuse by other tests. - Link to v4: https://lore.kernel.org/r/20231128-clone3-shadow-stack-v4-0-8b28ffe4f676@ke… Changes in v4: - Formatting changes. - Use a define for minimum shadow stack size and move some basic validation to fork.c. - Link to v3: https://lore.kernel.org/r/20231120-clone3-shadow-stack-v3-0-a7b8ed3e2acc@ke… Changes in v3: - Rebase onto v6.7-rc2. - Remove stale shadow_stack in internal kargs. - If a shadow stack is specified unconditionally use it regardless of CLONE_ parameters. - Force enable shadow stacks in the selftest. - Update changelogs for RISC-V feature rename. - Link to v2: https://lore.kernel.org/r/20231114-clone3-shadow-stack-v2-0-b613f8681155@ke… Changes in v2: - Rebase onto v6.7-rc1. - Remove ability to provide preallocated shadow stack, just specify the desired size. - Link to v1: https://lore.kernel.org/r/20231023-clone3-shadow-stack-v1-0-d867d0b5d4d0@ke… --- Mark Brown (8): arm64/gcs: Return a success value from gcs_alloc_thread_stack() Documentation: userspace-api: Add shadow stack API documentation selftests: Provide helper header for shadow stack testing fork: Add shadow stack support to clone3() selftests/clone3: Remove redundant flushes of output streams selftests/clone3: Factor more of main loop into test_clone3() selftests/clone3: Allow tests to flag if -E2BIG is a valid error code selftests/clone3: Test shadow stack support Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/shadow_stack.rst | 41 ++++ arch/arm64/include/asm/gcs.h | 8 +- arch/arm64/kernel/process.c | 8 +- arch/arm64/mm/gcs.c | 62 +++++- arch/x86/include/asm/shstk.h | 11 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 57 +++++- include/asm-generic/cacheflush.h | 11 ++ include/linux/sched/task.h | 17 ++ include/uapi/linux/sched.h | 10 +- kernel/fork.c | 96 +++++++-- tools/testing/selftests/clone3/clone3.c | 226 ++++++++++++++++++---- tools/testing/selftests/clone3/clone3_selftests.h | 65 ++++++- tools/testing/selftests/ksft_shstk.h | 98 ++++++++++ 15 files changed, 632 insertions(+), 81 deletions(-) --- base-commit: d17cd7b7cc92d37ee8b2df8f975fc859a261f4dc change-id: 20231019-clone3-shadow-stack-15d40d2bf536 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

3
12
0 0

[PATCH bpf-next] selftests/bpf: Fix compile error when MPTCP not support

by Tao Chen

Fix compile error when MPTCP feature not support, though eBPF core check already done which seems invalid in this situation, the error info like: progs/mptcp_sock.c:49:40: error: no member named 'is_mptcp' in 'struct tcp_sock' 49 | is_mptcp = bpf_core_field_exists(tsk->is_mptcp) ? The filed created in new definitions with eBPF core feature to solve this build problem, and test case result still ok in MPTCP kernel. 176/1 mptcp/base:OK 176/2 mptcp/mptcpify:OK 176 mptcp:OK Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED Fixes: 8039d353217c ("selftests/bpf: Add MPTCP test base") Signed-off-by: Tao Chen <chen.dylane(a)gmail.com> --- .../testing/selftests/bpf/progs/mptcp_sock.c | 42 ++++++++++++++----- 1 file changed, 32 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c index f3acb90588c7..2f80d042686a 100644 --- a/tools/testing/selftests/bpf/progs/mptcp_sock.c +++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c @@ -25,13 +25,23 @@ struct { __type(value, struct mptcp_storage); } socket_storage_map SEC(".maps"); +struct tcp_sock___new { + bool is_mptcp; +} __attribute__((preserve_access_index)); + +struct mptcp_sock___new { + __u32 token; + struct sock *first; + char ca_name[TCP_CA_NAME_MAX]; +} __attribute__((preserve_access_index)); + SEC("sockops") int _sockops(struct bpf_sock_ops *ctx) { struct mptcp_storage *storage; - struct mptcp_sock *msk; + struct mptcp_sock___new *msk; int op = (int)ctx->op; - struct tcp_sock *tsk; + struct tcp_sock___new *tsk; struct bpf_sock *sk; bool is_mptcp; @@ -42,11 +52,16 @@ int _sockops(struct bpf_sock_ops *ctx) if (!sk) return 1; - tsk = bpf_skc_to_tcp_sock(sk); + /* recast pointer to capture new type for compiler */ + tsk = (void *)bpf_skc_to_tcp_sock(sk); if (!tsk) return 1; - is_mptcp = bpf_core_field_exists(tsk->is_mptcp) ? tsk->is_mptcp : 0; + if (bpf_core_field_exists(tsk->is_mptcp)) + is_mptcp = BPF_CORE_READ(tsk, is_mptcp); + else + is_mptcp = 0; + if (!is_mptcp) { storage = bpf_sk_storage_get(&socket_storage_map, sk, 0, BPF_SK_STORAGE_GET_F_CREATE); @@ -57,7 +72,7 @@ int _sockops(struct bpf_sock_ops *ctx) __builtin_memset(storage->ca_name, 0, TCP_CA_NAME_MAX); storage->first = NULL; } else { - msk = bpf_skc_to_mptcp_sock(sk); + msk = (void *)bpf_skc_to_mptcp_sock(sk); if (!msk) return 1; @@ -66,9 +81,9 @@ int _sockops(struct bpf_sock_ops *ctx) if (!storage) return 1; - storage->token = msk->token; - __builtin_memcpy(storage->ca_name, msk->ca_name, TCP_CA_NAME_MAX); - storage->first = msk->first; + storage->token = BPF_CORE_READ(msk, token); + BPF_CORE_READ_STR_INTO(&storage->ca_name, msk, ca_name); + storage->first = BPF_CORE_READ(msk, first); } storage->invoked++; storage->is_mptcp = is_mptcp; @@ -81,8 +96,15 @@ SEC("fentry/mptcp_pm_new_connection") int BPF_PROG(trace_mptcp_pm_new_connection, struct mptcp_sock *msk, const struct sock *ssk, int server_side) { - if (!server_side) - token = msk->token; + struct mptcp_sock___new *mskw; + + if (!server_side) { + mskw = (void *)msk; + if (bpf_core_field_exists(mskw->token)) + token = BPF_CORE_READ(mskw, token); + else + token = 0; + } return 0; } -- 2.43.0

1 year, 1 month

3
4
0 0

[PATCH 0/3] Tracefs gid mount option fixes

by Kalesh Singh

Hi all, This series is based on v6.12-rc4. It fixes an issue with the tracefs gid mount option. Adds test case to prevent future breakages and updates the tracefs readme to document the expected behavior of this option. Thanks, Kalesh Kalesh Singh (3): tracing: Document tracefs gid mount option tracing/selftests: Add tracefs mount options test tracing: Fix tracefs gid mount option fs/tracefs/inode.c | 12 ++- kernel/trace/trace.c | 4 + .../ftrace/test.d/00basic/mount_options.tc | 101 ++++++++++++++++++ .../ftrace/test.d/00basic/test_ownership.tc | 16 +-- .../testing/selftests/ftrace/test.d/functions | 25 +++++ 5 files changed, 142 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc base-commit: 42f7652d3eb527d03665b09edac47f85fb600924 -- 2.47.0.163.g1226f6d8fa-goog

1 year, 1 month

3
9
0 0

[PATCH v2 0/3] Tracefs mount option fixes

by Kalesh Singh

Hi all, This is v2 of the series fixing the tracefs mount options. Changes in v2: - Update the commit descriptions, per Eric and Steve - Fix ordering of the patches, per Steve v1 can be found at: - https://lore.kernel.org/r/20241028214550.2099923-1-kaleshsingh@google.com/ Thanks, Kalesh Kalesh Singh (3): tracing: Fix tracefs mount options tracing: Document tracefs gid mount option tracing/selftests: Add tracefs mount options test fs/tracefs/inode.c | 12 ++- kernel/trace/trace.c | 4 + .../ftrace/test.d/00basic/mount_options.tc | 101 ++++++++++++++++++ .../ftrace/test.d/00basic/test_ownership.tc | 16 +-- .../testing/selftests/ftrace/test.d/functions | 25 +++++ 5 files changed, 142 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc base-commit: 42f7652d3eb527d03665b09edac47f85fb600924 -- 2.47.0.163.g1226f6d8fa-goog

1 year, 1 month

1
3
0 0

[PATCH] selftests/lam: Test get_user() LAM pointer handling

by Maciej Wieczor-Retman

Recent change in how get_user() handles pointers [1] has a specific case for LAM. It assigns a different bitmask that's later used to check whether a pointer comes from userland in get_user(). While currently commented out (until LASS [2] is merged into the kernel) it's worth making changes to the LAM selftest ahead of time. Add test case to LAM that utilizes a ioctl (FIOASYNC) syscall which uses get_user() in its implementation. Execute the syscall with differently tagged pointers to verify that valid user pointers are passing through and invalid kernel/non-canonical pointers are not. Code was tested on a Sierra Forest Xeon machine that's LAM capable. The test was ran without issues with both the LAM lines from [1] untouched and commented out. The test was also ran without issues with LAM_SUP both enabled and disabled. [1] https://lore.kernel.org/all/20241024013214.129639-1-torvalds@linux-foundati… [2] https://lore.kernel.org/all/20240710160655.3402786-1-alexander.shishkin@lin… Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman(a)intel.com> --- tools/testing/selftests/x86/lam.c | 85 +++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..3c53d4b7aa61 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -4,6 +4,7 @@ #include <stdlib.h> #include <string.h> #include <sys/syscall.h> +#include <sys/ioctl.h> #include <time.h> #include <signal.h> #include <setjmp.h> @@ -43,10 +44,19 @@ #define FUNC_INHERITE 0x20 #define FUNC_PASID 0x40 +/* get_user() pointer test cases */ +#define GET_USER_USER 0 +#define GET_USER_KERNEL_TOP 1 +#define GET_USER_KERNEL_BOT 2 +#define GET_USER_KERNEL 3 + #define TEST_MASK 0x7f +#define L5_SIGN_EXT_MASK (0xFFUL << 56) +#define L4_SIGN_EXT_MASK (0x1FFFFUL << 47) #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) +#define L5_ADDR (0x1UL << 48) #define MALLOC_LEN 32 @@ -370,6 +380,54 @@ static int handle_syscall(struct testcases *test) return ret; } +static int get_user_syscall(struct testcases *test) +{ + int ret = 0; + int ptr_value = 0; + void *ptr = &ptr_value; + int fd; + + uint64_t bitmask = ((uint64_t)ptr & L5_ADDR) ? L5_SIGN_EXT_MASK : + L4_SIGN_EXT_MASK; + + if (test->lam != 0) + if (set_lam(test->lam) != 0) + return 2; + + fd = memfd_create("lam_ioctl", 0); + if (fd == -1) + exit(EXIT_FAILURE); + + switch (test->later) { + case GET_USER_USER: + /* Control group - properly tagger user pointer */ + ptr = (void *)set_metadata((uint64_t)ptr, test->lam); + break; + case GET_USER_KERNEL_TOP: + /* Kernel address with top bit cleared */ + bitmask &= (bitmask >> 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL_BOT: + /* Kernel address with bottom sign-extension bit cleared */ + bitmask &= (bitmask << 1); + ptr = (void *)((uint64_t)ptr | bitmask); + break; + case GET_USER_KERNEL: + /* Try to pass a kernel address */ + ptr = (void *)((uint64_t)ptr | bitmask); + break; + default: + printf("Invalid test case value passed!\n"); + break; + } + + if (ioctl(fd, FIOASYNC, ptr) != 0) + ret = 1; + + return ret; +} + int sys_uring_setup(unsigned int entries, struct io_uring_params *p) { return (int)syscall(__NR_io_uring_setup, entries, p); @@ -883,6 +941,33 @@ static struct testcases syscall_cases[] = { .test_func = handle_syscall, .msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", }, + { + .later = GET_USER_USER, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n", + }, + { + .later = GET_USER_KERNEL_TOP, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n", + }, + { + .later = GET_USER_KERNEL_BOT, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n", + }, + { + .later = GET_USER_KERNEL, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = get_user_syscall, + .msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n", + }, }; static struct testcases mmap_cases[] = { -- 2.46.2

1 year, 1 month

2
2
0 0

[PATCH v5 00/13] iommufd: Add vIOMMU infrastructure (Part-1)

by Nicolin Chen

This series introduces a new vIOMMU infrastructure and related ioctls. IOMMUFD has been using the HWPT infrastructure for all cases, including a nested IO page table support. Yet, there're limitations for an HWPT-based structure to support some advanced HW-accelerated features, such as CMDQV on NVIDIA Grace, and HW-accelerated vIOMMU on AMD. Even for a multi-IOMMU environment, it is not straightforward for nested HWPTs to share the same parent HWPT (stage-2 IO pagetable), with the HWPT infrastructure alone: a parent HWPT typically hold one stage-2 IO pagetable and tag it with only one ID in the cache entries. When sharing one large stage-2 IO pagetable across physical IOMMU instances, that one ID may not always be available across all the IOMMU instances. In other word, it's ideal for SW to have a different container for the stage-2 IO pagetable so it can hold another ID that's available. And this container will be able to hold some advanced feature too. For this "different container", add vIOMMU, an additional layer to hold extra virtualization information: _______________________________________________________________________ | iommufd (with vIOMMU) | | _____________ | | | | | | |----------------| vIOMMU | | | | ______ | | _____________ ________ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | | | | | | | | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| The vIOMMU object should be seen as a slice of a physical IOMMU instance that is passed to or shared with a VM. That can be some HW/SW resources: - Security namespace for guest owned ID, e.g. guest-controlled cache tags - Access to a sharable nesting parent pagetable across physical IOMMUs - Non-affiliated event reporting (e.g. an invalidation queue error) - Virtualization of various platforms IDs, e.g. RIDs and others - Delivery of paravirtualized invalidation - Direct assigned invalidation queues - Direct assigned interrupts On a multi-IOMMU system, the vIOMMU object must be instanced to the number of the physical IOMMUs that have a slice passed to (via device) a guest VM, while being able to hold the shareable parent HWPT. Each vIOMMU then just needs to allocate its own individual ID to tag its own cache: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | IDx | ---------------------------- ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested1 |--->| viommu1 ------------------ ---------------- | | IDy | ---------------------------- As an initial part-1, add IOMMUFD_CMD_VIOMMU_ALLOC ioctl for an allocation only. And implement it in arm-smmu-v3 driver as a real world use case. More vIOMMU-based structs and ioctls will be introduced in the follow-up series to support vDEVICE, vIRQ (vEVENT) and vQUEUE objects. Although we repurposed the vIOMMU object from an earlier RFC, just for a referece: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p1-v5 (paring QEMU branch for testing will be provided with the part2 series) Changelog v5 * Added "Reviewed-by" from Kevin * Reworked iommufd_viommu_alloc helper * Revised the uAPI kdoc for vIOMMU object * Revised comments for pluggable iommu_dev * Added a couple of cleanup patches for selftest * Renamed domain_alloc_nested op to alloc_domain_nested * Updated a few commit messages to reflect the latest series * Renamed iommufd_hwpt_nested_alloc_for_viommu to iommufd_viommu_alloc_hwpt_nested, and added flag validation v4 https://lore.kernel.org/all/cover.1729553811.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Jason * Dropped IOMMU_VIOMMU_TYPE_DEFAULT support * Dropped iommufd_object_alloc_elm renamings * Renamed iommufd's viommu_api.c to driver.c * Reworked iommufd_viommu_alloc helper * Added a separate iommufd_hwpt_nested_alloc_for_viommu function for hwpt_nested allocations on a vIOMMU, and added comparison between viommu->iommu_dev->ops and dev_iommu_ops(idev->dev) * Replaced s2_parent with vsmmu in arm_smmu_nested_domain * Replaced domain_alloc_user in iommu_ops with domain_alloc_nested in viommu_ops * Replaced wait_queue_head_t with a completion, to delay the unplug of mock_iommu_dev * Corrected documentation graph that was missing struct iommu_device * Added an iommufd_verify_unfinalized_object helper to verify driver- allocated vIOMMU/vDEVICE objects * Added missing test cases for TEST_LENGTH and fail_nth v3 https://lore.kernel.org/all/cover.1728491453.git.nicolinc@nvidia.com/ * Rebased on top of Jason's nesting v3 series https://lore.kernel.org/all/0-v3-e2e16cd7467f+2a6a1-smmuv3_nesting_jgg@nvid… * Split the series into smaller parts * Added Jason's Reviewed-by * Added back viommu->iommu_dev * Added support for driver-allocated vIOMMU v.s. core-allocated * Dropped arm_smmu_cache_invalidate_user * Added an iommufd_test_wait_for_users() in selftest * Reworked test code to make viommu an individual FIXTURE * Added missing TEST_LENGTH case for the new ioctl command v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (13): iommufd: Move struct iommufd_object to public iommufd header iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct iommufd: Add iommufd_verify_unfinalized_object iommufd/viommu: Add IOMMU_VIOMMU_ALLOC ioctl iommufd: Add alloc_domain_nested op to iommufd_viommu_ops iommufd: Allow pt_id to carry viommu_id for IOMMU_HWPT_ALLOC iommufd/selftest: Add container_of helpers iommufd/selftest: Prepare for mock_viommu_alloc_domain_nested() iommufd/selftest: Add refcount to mock_iommu_device iommufd/selftest: Add IOMMU_VIOMMU_TYPE_SELFTEST iommufd/selftest: Add IOMMU_VIOMMU_ALLOC test coverage Documentation: userspace-api: iommufd: Update vIOMMU iommu/arm-smmu-v3: Add IOMMU_VIOMMU_TYPE_ARM_SMMUV3 support drivers/iommu/iommufd/Makefile | 5 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 26 +- drivers/iommu/iommufd/iommufd_private.h | 36 +-- drivers/iommu/iommufd/iommufd_test.h | 2 + include/linux/iommu.h | 14 + include/linux/iommufd.h | 86 ++++++ include/uapi/linux/iommufd.h | 56 +++- tools/testing/selftests/iommu/iommufd_utils.h | 28 ++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 80 ++++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 +- drivers/iommu/iommufd/driver.c | 38 +++ drivers/iommu/iommufd/hw_pagetable.c | 71 ++++- drivers/iommu/iommufd/main.c | 58 ++-- drivers/iommu/iommufd/selftest.c | 256 ++++++++++++------ drivers/iommu/iommufd/viommu.c | 89 ++++++ tools/testing/selftests/iommu/iommufd.c | 87 ++++++ .../selftests/iommu/iommufd_fail_nth.c | 11 + Documentation/userspace-api/iommufd.rst | 69 ++++- 18 files changed, 827 insertions(+), 194 deletions(-) create mode 100644 drivers/iommu/iommufd/driver.c create mode 100644 drivers/iommu/iommufd/viommu.c -- 2.43.0

1 year, 1 month

4
52
0 0

[PATCH] selftests: netfilter: remove unused parameter

by Liu Jing

Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- V1 -> V2: Delete more unused parameters, such as err, v1 only deleted rplnlh parameter Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- .../testing/selftests/net/netfilter/conntrack_dump_flush.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index e03ddc60b5d4..63ae49f166a1 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -97,7 +97,7 @@ static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh, { char buf[MNL_SOCKET_BUFFER_SIZE]; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -215,7 +215,7 @@ static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -262,7 +262,7 @@ static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); -- 2.27.0

1 year, 1 month

2
1
0 0

[PATCH][next] KVM: s390: selftests: Fix spelling mistake "avaialable" -> "available"

by Colin Ian King

There is a spelling mistake in a ksft_test_result_skip message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c index 222ba1cc3cac..34e0ceceaa74 100644 --- a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c +++ b/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c @@ -276,7 +276,7 @@ int main(int argc, char *argv[]) ksft_test_result_pass("%s\n", testlist[idx].subfunc_name); free(array); } else { - ksft_test_result_skip("%s feature is not avaialable\n", + ksft_test_result_skip("%s feature is not available\n", testlist[idx].subfunc_name); } } -- 2.39.5

1 year, 1 month

1
0
0 0

[PATCH v2 0/3] rust: kunit: Support KUnit tests with a user-space like syntax

by David Gow

This series was originally written by José Expósito, and has been modified and updated by Matt Gilbride and myself. The original version can be found here: https://github.com/Rust-for-Linux/linux/pull/950 Add support for writing KUnit tests in Rust. While Rust doctests are already converted to KUnit tests and run, they're really better suited for examples, rather than as first-class unit tests. This series implements a series of direct Rust bindings for KUnit tests, as well as a new macro which allows KUnit tests to be written using a close variant of normal Rust unit test syntax. The only change required is replacing '#[cfg(test)]' with '#[kunit_tests(kunit_test_suite_name)]' An example test would look like: #[kunit_tests(rust_kernel_hid_driver)] mod tests { use super::*; use crate::{c_str, driver, hid, prelude::*}; use core::ptr; struct SimpleTestDriver; impl Driver for SimpleTestDriver { type Data = (); } #[test] fn rust_test_hid_driver_adapter() { let mut hid = bindings::hid_driver::default(); let name = c_str!("SimpleTestDriver"); static MODULE: ThisModule = unsafe { ThisModule::from_ptr(ptr::null_mut()) }; let res = unsafe { <hid::Adapter<SimpleTestDriver> as driver::DriverOps>::register(&mut hid, name, &MODULE) }; assert_eq!(res, Err(ENODEV)); // The mock returns -19 } } Please give this a go, and make sure I haven't broken it! There's almost certainly a lot of improvements which can be made -- and there's a fair case to be made for replacing some of this with generated C code which can use the C macros -- but this is hopefully an adequate implementation for now, and the interface can (with luck) remain the same even if the implementation changes. A few small notable missing features: - Attributes (like the speed of a test) are hardcoded to the default value. - Similarly, the module name attribute is hardcoded to NULL. In C, we use the KBUILD_MODNAME macro, but I couldn't find a way to use this from Rust which wasn't more ugly than just disabling it. - Assertions are not automatically rewritten to use KUnit assertions. --- Changes since v1: https://lore.kernel.org/lkml/20230720-rustbind-v1-0-c80db349e3b5@google.com… - Rebase on top of the latest rust-next (commit 718c4069896c) - Make kunit_case a const fn, rather than a macro (Thanks Boqun) - As a result, the null terminator is now created with kernel::kunit::kunit_case_null() - Use the C kunit_get_current_test() function to implement in_kunit_test(), rather than re-implementing it (less efficiently) ourselves. Changes since the GitHub PR: - Rebased on top of kselftest/kunit - Add const_mut_refs feature This may conflict with https://lore.kernel.org/lkml/20230503090708.2524310-6-nmi@metaspace.dk/ - Add rust/macros/kunit.rs to the KUnit MAINTAINERS entry --- José Expósito (3): rust: kunit: add KUnit case and suite macros rust: macros: add macro to easily run KUnit tests rust: kunit: allow to know if we are in a test MAINTAINERS | 1 + rust/kernel/kunit.rs | 191 +++++++++++++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + rust/macros/lib.rs | 29 +++++++ 4 files changed, 222 insertions(+) -- 2.47.0.163.g1226f6d8fa-goog

1 year, 1 month

3
8
0 0

[PATCH] selftest/hid: increase timeout to 10 min

by Yun Lu

If running hid testcases with command "./run_kselftest.sh -c hid", the following tests will take longer than the kselftest framework timeout (now 200 seconds) to run and thus got terminated with TIMEOUT error: hid-multitouch.sh - took about 6min41s hid-tablet.sh - took about 6min30s Increase the timeout setting to 10 minutes to allow them have a chance to finish. Cc: stable(a)vger.kernel.org Signed-off-by: Yun Lu <luyun(a)kylinos.cn> --- tools/testing/selftests/hid/settings | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/hid/settings b/tools/testing/selftests/hid/settings index b3cbfc521b10..dff0d947f9c2 100644 --- a/tools/testing/selftests/hid/settings +++ b/tools/testing/selftests/hid/settings @@ -1,3 +1,3 @@ # HID tests can be long, so give a little bit more time # to them -timeout=200 +timeout=600 -- 2.27.0

1 year, 1 month

3
2
0 0

[PATCH bpf-next v2] selftests/bpf: Drop netns helpers in mptcp

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> New netns selftest helpers netns_new() and netns_free() has been added in network_helpers.c, let's use them in mptcp selftests too instead of using MPTCP's own helpers create_netns() and cleanup_netns(). Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> --- v2: - Use netns_new/netns_free instead of create_netns/cleanup_netns as Martin suggested. v1: selftests/bpf: Use make/remove netns helpers in mptcp --- .../testing/selftests/bpf/prog_tests/mptcp.c | 42 ++++++------------- 1 file changed, 12 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index be3cad2aff77..f8eb7f9d4fd2 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -69,24 +69,6 @@ struct mptcp_storage { char ca_name[TCP_CA_NAME_MAX]; }; -static struct nstoken *create_netns(void) -{ - SYS(fail, "ip netns add %s", NS_TEST); - SYS(fail, "ip -net %s link set dev lo up", NS_TEST); - - return open_netns(NS_TEST); -fail: - return NULL; -} - -static void cleanup_netns(struct nstoken *nstoken) -{ - if (nstoken) - close_netns(nstoken); - - SYS_NOFAIL("ip netns del %s", NS_TEST); -} - static int start_mptcp_server(int family, const char *addr_str, __u16 port, int timeout_ms) { @@ -206,15 +188,15 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp) static void test_base(void) { - struct nstoken *nstoken = NULL; + struct netns_obj *netns = NULL; int server_fd, cgroup_fd; cgroup_fd = test__join_cgroup("/mptcp"); if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new")) goto fail; /* without MPTCP */ @@ -237,7 +219,7 @@ static void test_base(void) close(server_fd); fail: - cleanup_netns(nstoken); + netns_free(netns); close(cgroup_fd); } @@ -322,21 +304,21 @@ static int run_mptcpify(int cgroup_fd) static void test_mptcpify(void) { - struct nstoken *nstoken = NULL; + struct netns_obj *netns = NULL; int cgroup_fd; cgroup_fd = test__join_cgroup("/mptcpify"); if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup")) return; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new")) goto fail; ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify"); fail: - cleanup_netns(nstoken); + netns_free(netns); close(cgroup_fd); } @@ -414,7 +396,7 @@ static void run_subflow(void) static void test_subflow(void) { struct mptcp_subflow *skel; - struct nstoken *nstoken; + struct netns_obj *netns; int cgroup_fd; cgroup_fd = test__join_cgroup("/mptcp_subflow"); @@ -437,8 +419,8 @@ static void test_subflow(void) if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow")) goto skel_destroy; - nstoken = create_netns(); - if (!ASSERT_OK_PTR(nstoken, "create_netns: mptcp_subflow")) + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_subflow")) goto skel_destroy; if (endpoint_init("subflow") < 0) @@ -447,7 +429,7 @@ static void test_subflow(void) run_subflow(); close_netns: - cleanup_netns(nstoken); + netns_free(netns); skel_destroy: mptcp_subflow__destroy(skel); close_cgroup: -- 2.45.2

1 year, 1 month

1
0
0 0

[PATCH v5 00/13] iommufd: Add vIOMMU infrastructure (Part-2: vDEVICE)

by Nicolin Chen

Following the previous vIOMMU series, this adds another vDEVICE structure, representing the association from an iommufd_device to an iommufd_viommu. This gives the whole architecture a new "v" layer: _______________________________________________________________________ | iommufd (with vIOMMU/vDEVICE) | | _____________ _____________ | | | | | | | | |----------------| vIOMMU |<---| vDEVICE |<------| | | | | | |_____________| | | | | ______ | | _____________ ___|____ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| This vDEVICE object is used to collect and store all vIOMMU-related device information/attributes in a VM. As an initial series for vDEVICE, add only the virt_id to the vDEVICE, which is a vIOMMU specific device ID in a VM: e.g. vSID of ARM SMMUv3, vDeviceID of AMD IOMMU, and vID of Intel VT-d to a Context Table. This virt_id helps IOMMU drivers to link the vID to a pID of the device against the physical IOMMU instance. This is essential for a vIOMMU-based invalidation, where the request contains a device's vID for a device cache flush, e.g. ATC invalidation. Therefore, with this vDEVICE object, support a vIOMMU-based invalidation, by reusing IOMMUFD_CMD_HWPT_INVALIDATE for a vIOMMU object to flush cache with a given driver data. As for the implementation of the series, add driver support in ARM SMMUv3 for a real world use case. This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p2-v5 For testing, try this "with-rmr" branch: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p2-v5-with-rmr Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_viommu_p2-v5 Changelog v5 * Dropped driver-allocated vDEVICE support * Changed vdev_to_dev helper to iommufd_viommu_find_dev v4 https://lore.kernel.org/all/cover.1729555967.git.nicolinc@nvidia.com/ * Added missing brackets in switch-case * Fixed the unreleased idev refcount issue * Reworked the iommufd_vdevice_alloc allocator * Dropped support for IOMMU_VIOMMU_TYPE_DEFAULT * Added missing TEST_LENGTH and fail_nth coverages * Added a verification to the driver-allocated vDEVICE object * Added an iommufd_vdevice_abort for a missing mutex protection * Added a u64 structure arm_vsmmu_invalidation_cmd for user command conversion v3 https://lore.kernel.org/all/cover.1728491532.git.nicolinc@nvidia.com/ * Added Jason's Reviewed-by * Split this invalidation part out of the part-1 series * Repurposed VDEV_ID ioctl to a wider vDEVICE structure and ioctl * Reduced viommu_api functions by allowing drivers to access viommu and vdevice structure directly * Dropped vdevs_rwsem by using xa_lock instead * Dropped arm_smmu_cache_invalidate_user v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Jason Gunthorpe (2): iommu: Add iommu_copy_struct_from_full_user_array helper iommu/arm-smmu-v3: Allow ATS for IOMMU_DOMAIN_NESTED Nicolin Chen (11): iommufd/viommu: Add IOMMUFD_OBJ_VDEVICE and IOMMU_VDEVICE_ALLOC ioctl iommufd/selftest: Add IOMMU_VDEVICE_ALLOC test coverage iommu/viommu: Add cache_invalidate to iommufd_viommu_ops iommufd/hw_pagetable: Enforce invalidation op on vIOMMU-based hwpt_nested iommufd: Allow hwpt_id to carry viommu_id for IOMMU_HWPT_INVALIDATE iommufd/viommu: Add iommufd_viommu_find_dev helper iommufd/selftest: Add mock_viommu_cache_invalidate iommufd/selftest: Add IOMMU_TEST_OP_DEV_CHECK_CACHE test command iommufd/selftest: Add vIOMMU coverage for IOMMU_HWPT_INVALIDATE ioctl Documentation: userspace-api: iommufd: Update vDEVICE iommu/arm-smmu-v3: Add arm_vsmmu_cache_invalidate drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 9 +- drivers/iommu/iommufd/iommufd_private.h | 20 ++ drivers/iommu/iommufd/iommufd_test.h | 30 +++ include/linux/iommu.h | 48 ++++- include/linux/iommufd.h | 21 ++ include/uapi/linux/iommufd.h | 61 +++++- tools/testing/selftests/iommu/iommufd_utils.h | 83 +++++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 161 +++++++++++++- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 32 ++- drivers/iommu/iommufd/device.c | 11 + drivers/iommu/iommufd/driver.c | 13 ++ drivers/iommu/iommufd/hw_pagetable.c | 36 +++- drivers/iommu/iommufd/main.c | 7 + drivers/iommu/iommufd/selftest.c | 98 ++++++++- drivers/iommu/iommufd/viommu.c | 101 +++++++++ tools/testing/selftests/iommu/iommufd.c | 204 +++++++++++++++++- .../selftests/iommu/iommufd_fail_nth.c | 4 + Documentation/userspace-api/iommufd.rst | 41 +++- 18 files changed, 942 insertions(+), 38 deletions(-) -- 2.43.0

1 year, 1 month

4
43
0 0

[PATCH v3] selftests/net: Add missing gitignore file

by Li Zhijian

Compiled binary files should be added to .gitignore 'git status' complains: Untracked files: (use "git add <file>..." to include in what will be committed) net/netfilter/conntrack_reverse_clash Cc: Pablo Neira Ayuso <pablo(a)netfilter.org> Cc: Jozsef Kadlecsik <kadlec(a)netfilter.org> 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: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- Cc: netfilter-devel(a)vger.kernel.org Cc: coreteam(a)netfilter.org Cc: netdev(a)vger.kernel.org --- Hello, Cover letter is here. This patch set aims to make 'git status' clear after 'make' and 'make run_tests' for kselftests. --- V3: sort the files V2: split as a separate patch from a small one [0] [0] https://lore.kernel.org/linux-kselftest/20241015010817.453539-1-lizhijian@f… Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- tools/testing/selftests/net/netfilter/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore index 0a64d6d0e29a..64c4f8d9aa6c 100644 --- a/tools/testing/selftests/net/netfilter/.gitignore +++ b/tools/testing/selftests/net/netfilter/.gitignore @@ -2,5 +2,6 @@ audit_logread connect_close conntrack_dump_flush +conntrack_reverse_clash sctp_collision nf_queue -- 2.44.0

1 year, 1 month

1
0
0 0

[PATCH for-next 1/7] selftests/alsa: Add a few missing gitignore files

by Li Zhijian

Compiled binary files should be added to .gitignore 'git status' complains: Untracked files: (use "git add <file>..." to include in what will be committed) alsa/global-timer alsa/utimer-test Cc: Mark Brown <broonie(a)kernel.org> Cc: Jaroslav Kysela <perex(a)perex.cz> Cc: Takashi Iwai <tiwai(a)suse.com> Cc: Shuah Khan <shuah(a)kernel.org> Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- Cc: linux-sound(a)vger.kernel.org --- Hello, Cover letter is here. This patch set aims to make 'git status' clear after 'make' and 'make run_tests' for kselftests. --- V2: split as a separate patch from a small one [0] [0] https://lore.kernel.org/linux-kselftest/20241015010817.453539-1-lizhijian@f… --- tools/testing/selftests/alsa/.gitignore | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore index 12dc3fcd3456..1407fd24a97b 100644 --- a/tools/testing/selftests/alsa/.gitignore +++ b/tools/testing/selftests/alsa/.gitignore @@ -1,3 +1,5 @@ mixer-test pcm-test test-pcmtest-driver +global-timer +utimer-test -- 2.44.0

1 year, 1 month

5
13
0 0

[PATCH net-next v5 00/12] selftests: ncdevmem: Add ncdevmem to ksft

by Stanislav Fomichev

The goal of the series is to simplify and make it possible to use ncdevmem in an automated way from the ksft python wrapper. ncdevmem is slowly mutated into a state where it uses stdout to print the payload and the python wrapper is added to make sure the arrived payload matches the expected one. v5: - properly handle errors from inet_pton() and socket() (Paolo) - remove unneeded import from python selftest (Paolo) v4: - keep usage example with validation (Mina) - fix compilation issue in one patch (s/start_queues/start_queue/) v3: - keep and refine the comment about ncdevmem invocation (Mina) - add the comment about not enforcing exit status for ntuple reset (Mina) - make configure_headersplit more robust (Mina) - use num_queues/2 in selftest and let the users override it (Mina) - remove memory_provider.memcpy_to_device (Mina) - keep ksft as is (don't use -v validate flags): we are gonna need a --debug-disable flag to make it less chatty; otherwise it times out when sending too much data; so leaving it as a separate follow up v2: - don't remove validation (Mina) - keep 5-tuple flow steering but use it only when -c is provided (Mina) - remove separate flag for probing (Mina) - move ncdevmem under drivers/net/hw, not drivers/net (Jakub) Cc: Mina Almasry <almasrymina(a)google.com> Stanislav Fomichev (12): selftests: ncdevmem: Redirect all non-payload output to stderr selftests: ncdevmem: Separate out dmabuf provider selftests: ncdevmem: Unify error handling selftests: ncdevmem: Make client_ip optional selftests: ncdevmem: Remove default arguments selftests: ncdevmem: Switch to AF_INET6 selftests: ncdevmem: Properly reset flow steering selftests: ncdevmem: Use YNL to enable TCP header split selftests: ncdevmem: Remove hard-coded queue numbers selftests: ncdevmem: Run selftest when none of the -s or -c has been provided selftests: ncdevmem: Move ncdevmem under drivers/net/hw selftests: ncdevmem: Add automated test .../selftests/drivers/net/hw/.gitignore | 1 + .../testing/selftests/drivers/net/hw/Makefile | 9 + .../selftests/drivers/net/hw/devmem.py | 45 + .../selftests/drivers/net/hw/ncdevmem.c | 773 ++++++++++++++++++ tools/testing/selftests/net/.gitignore | 1 - tools/testing/selftests/net/Makefile | 8 - tools/testing/selftests/net/ncdevmem.c | 570 ------------- 7 files changed, 828 insertions(+), 579 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/.gitignore create mode 100755 tools/testing/selftests/drivers/net/hw/devmem.py create mode 100644 tools/testing/selftests/drivers/net/hw/ncdevmem.c delete mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.47.0

1 year, 1 month

3
14
0 0

[PATCH v6 00/33] riscv control-flow integrity for usermode

by Deepak Gupta

Basics and overview =================== Software with larger attack surfaces (e.g. network facing apps like databases, browsers or apps relying on browser runtimes) suffer from memory corruption issues which can be utilized by attackers to bend control flow of the program to eventually gain control (by making their payload executable). Attackers are able to perform such attacks by leveraging call-sites which rely on indirect calls or return sites which rely on obtaining return address from stack memory. To mitigate such attacks, risc-v extension zicfilp enforces that all indirect calls must land on a landing pad instruction `lpad` else cpu will raise software check exception (a new cpu exception cause code on riscv). Similarly for return flow, risc-v extension zicfiss extends architecture with - `sspush` instruction to push return address on a shadow stack - `sspopchk` instruction to pop return address from shadow stack and compare with input operand (i.e. return address on stack) - `sspopchk` to raise software check exception if comparision above was a mismatch - Protection mechanism using which shadow stack is not writeable via regular store instructions More information an details can be found at extensions github repo [1]. Equivalent to landing pad (zicfilp) on x86 is `ENDBRANCH` instruction in Intel CET [3] and branch target identification (BTI) [4] on arm. Similarly x86's Intel CET has shadow stack [5] and arm64 has guarded control stack (GCS) [6] which are very similar to risc-v's zicfiss shadow stack. x86 already supports shadow stack for user mode and arm64 support for GCS in usermode [7] is ongoing. Kernel awareness for user control flow integrity ================================================ This series picks up Samuel Holland's envcfg changes [2] as well. So if those are being applied independently, they should be removed from this series. Enabling: In order to maintain compatibility and not break anything in user mode, kernel doesn't enable control flow integrity cpu extensions on binary by default. Instead exposes a prctl interface to enable, disable and lock the shadow stack or landing pad feature for a task. This allows userspace (loader) to enumerate if all objects in its address space are compiled with shadow stack and landing pad support and accordingly enable the feature. Additionally if a subsequent `dlopen` happens on a library, user mode can take a decision again to disable the feature (if incoming library is not compiled with support) OR terminate the task (if user mode policy is strict to have all objects in address space to be compiled with control flow integirty cpu feature). prctl to enable shadow stack results in allocating shadow stack from virtual memory and activating for user address space. x86 and arm64 are also following same direction due to similar reason(s). clone/fork: On clone and fork, cfi state for task is inherited by child. Shadow stack is part of virtual memory and is a writeable memory from kernel perspective (writeable via a restricted set of instructions aka shadow stack instructions) Thus kernel changes ensure that this memory is converted into read-only when fork/clone happens and COWed when fault is taken due to sspush, sspopchk or ssamoswap. In case `CLONE_VM` is specified and shadow stack is to be enabled, kernel will automatically allocate a shadow stack for that clone call. map_shadow_stack: x86 introduced `map_shadow_stack` system call to allow user space to explicitly map shadow stack memory in its address space. It is useful to allocate shadow for different contexts managed by a single thread (green threads or contexts) risc-v implements this system call as well. signal management: If shadow stack is enabled for a task, kernel performs an asynchronous control flow diversion to deliver the signal and eventually expects userspace to issue sigreturn so that original execution can be resumed. Even though resume context is prepared by kernel, it is in user space memory and is subject to memory corruption and corruption bugs can be utilized by attacker in this race window to perform arbitrary sigreturn and eventually bypass cfi mechanism. Another issue is how to ensure that cfi related state on sigcontext area is not trampled by legacy apps or apps compiled with old kernel headers. In order to mitigate control-flow hijacting, kernel prepares a token and place it on shadow stack before signal delivery and places address of token in sigcontext structure. During sigreturn, kernel obtains address of token from sigcontext struture, reads token from shadow stack and validates it and only then allow sigreturn to succeed. Compatiblity issue is solved by adopting dynamic sigcontext management introduced for vector extension. This series re-factor the code little bit to allow future sigcontext management easy (as proposed by Andy Chiu from SiFive) config and compilation: Introduce a new risc-v config option `CONFIG_RISCV_USER_CFI`. Selecting this config option picks the kernel support for user control flow integrity. This optin is presented only if toolchain has shadow stack and landing pad support. And is on purpose guarded by toolchain support. Reason being that eventually vDSO also needs to be compiled in with shadow stack and landing pad support. vDSO compile patches are not included as of now because landing pad labeling scheme is yet to settle for usermode runtime. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` in following: Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- $ git clone git@github.com:deepak0414/qemu.git -b zicfilp_zicfiss_ratified_master_july11 $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) Branch where user cfi enabling patches are maintained https://github.com/deepak0414/linux-riscv-cfi/tree/vdso_user_cfi_v6.12-rc1 In case you're building your own rootfs using toolchain, please make sure you pick following patch to ensure that vDSO compiled with lpad and shadow stack. "arch/riscv: compile vdso with landing pad" Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. References ========== [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/all/20240814081126.956287-1-samuel.holland@sifive.c… [3] - https://lwn.net/Articles/889475/ [4] - https://developer.arm.com/documentation/109576/0100/Branch-Target-Identific… [5] - https://www.intel.com/content/dam/develop/external/us/en/documents/catc17-i… [6] - https://lwn.net/Articles/940403/ [7] - https://lore.kernel.org/all/20241001-arm64-gcs-v13-0-222b78d87eee@kernel.or… To: Thomas Gleixner <tglx(a)linutronix.de> To: Ingo Molnar <mingo(a)redhat.com> To: Borislav Petkov <bp(a)alien8.de> To: Dave Hansen <dave.hansen(a)linux.intel.com> To: x86(a)kernel.org To: H. Peter Anvin <hpa(a)zytor.com> To: Andrew Morton <akpm(a)linux-foundation.org> To: Liam R. Howlett <Liam.Howlett(a)oracle.com> To: Vlastimil Babka <vbabka(a)suse.cz> To: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> To: Paul Walmsley <paul.walmsley(a)sifive.com> To: Palmer Dabbelt <palmer(a)dabbelt.com> To: Albert Ou <aou(a)eecs.berkeley.edu> To: Conor Dooley <conor(a)kernel.org> To: Rob Herring <robh(a)kernel.org> To: Krzysztof Kozlowski <krzk+dt(a)kernel.org> To: Arnd Bergmann <arnd(a)arndb.de> To: Christian Brauner <brauner(a)kernel.org> To: Peter Zijlstra <peterz(a)infradead.org> To: Oleg Nesterov <oleg(a)redhat.com> To: Eric Biederman <ebiederm(a)xmission.com> To: Kees Cook <kees(a)kernel.org> To: Jonathan Corbet <corbet(a)lwn.net> To: Shuah Khan <shuah(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-fsdevel(a)vger.kernel.org Cc: linux-mm(a)kvack.org Cc: linux-riscv(a)lists.infradead.org Cc: devicetree(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-doc(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: alistair.francis(a)wdc.com Cc: richard.henderson(a)linaro.org Cc: jim.shu(a)sifive.com Cc: andybnac(a)gmail.com Cc: kito.cheng(a)sifive.com Cc: charlie(a)rivosinc.com Cc: atishp(a)rivosinc.com Cc: evan(a)rivosinc.com Cc: cleger(a)rivosinc.com Cc: alexghiti(a)rivosinc.com Cc: samitolvanen(a)google.com Cc: broonie(a)kernel.org Cc: rick.p.edgecombe(a)intel.com Signed-off-by: Deepak Gupta <debug(a)rivosinc.com> --- changelog --------- v6: - Picked up Samuel Holland's changes as is with `envcfg` placed in `thread` instead of `thread_info` - fixed unaligned newline escapes in kselftest - cleaned up messages in kselftest and included test output in commit message - fixed a bug in clone path reported by Zong Li - fixed a build issue if CONFIG_RISCV_ISA_V is not selected (this was introduced due to re-factoring signal context management code) v5: - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT (https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware…) - Link to v5: https://lore.kernel.org/r/20241001-v5_user_cfi_series-v1-0-3ba65b6e550f@riv… (Note: I had an issue in my workflow due to which version number wasn't picked up correctly while sending out patches) v4: - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. - Link to v4: https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ v3: - envcfg logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. - dt-bindings As suggested, split into separate commit. fixed the messaging that spec is in public review - arch_is_shadow_stack change arch_is_shadow_stack changed to vma_is_shadow_stack - hwprobe zicfiss / zicfilp if present will get enumerated in hwprobe - selftests As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. - Link to v3: https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ v2: - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Clément Léger (1): riscv: Add Firmware Feature SBI extensions definitions Deepak Gupta (26): mm: helper `is_shadow_stack_vma` to check shadow stack vma riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv dt-bindings: riscv: zicfilp and zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv mm: manufacture shadow stack pte riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs riscv mmu: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic shadow stack prctls riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception riscv/signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: kernel command line option to opt out of user cfi riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Mark Brown (2): mm: Introduce ARCH_HAS_USER_SHADOW_STACK prctl: arch-agnostic prctl for shadow stack Samuel Holland (3): riscv: Enable cbo.zero only when all harts support Zicboz riscv: Add support for per-thread envcfg CSR values riscv: Call riscv_user_isa_enable() only on the boot hart Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 176 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 21 + arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/cpufeature.h | 15 +- arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 24 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 3 + arch/riscv/include/asm/sbi.h | 27 ++ arch/riscv/include/asm/switch_to.h | 8 + arch/riscv/include/asm/thread_info.h | 3 + arch/riscv/include/asm/usercfi.h | 89 ++++ arch/riscv/include/asm/vector.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 22 + arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/asm-offsets.c | 8 + arch/riscv/kernel/cpufeature.c | 13 +- arch/riscv/kernel/entry.S | 31 +- arch/riscv/kernel/head.S | 12 + arch/riscv/kernel/process.c | 31 +- arch/riscv/kernel/ptrace.c | 83 ++++ arch/riscv/kernel/signal.c | 140 +++++- arch/riscv/kernel/smpboot.c | 2 - arch/riscv/kernel/suspend.c | 4 +- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 42 ++ arch/riscv/kernel/usercfi.c | 526 +++++++++++++++++++++ arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 17 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/cpu.h | 4 + include/linux/mm.h | 5 +- include/uapi/asm-generic/mman.h | 4 + include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 48 ++ kernel/sys.c | 60 +++ mm/Kconfig | 6 + mm/gup.c | 2 +- mm/mmap.c | 1 + mm/vma.h | 10 +- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 84 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 78 +++ tools/testing/selftests/riscv/cfi/shadowstack.c | 373 +++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 ++ 56 files changed, 2190 insertions(+), 42 deletions(-) --- base-commit: 7d9923ee3960bdbfaa7f3a4e0ac2364e770c46ff change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

1 year, 1 month

6
51
0 0

[PATCH bpf-next] selftests/bpf: Use make/remove netns helpers in mptcp

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> New netns selftest helpers make_netns() and remove_netns() has been added in network_helpers.c, let's use them in mptcp selftests too. Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/mptcp.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index d2ca32fa3b21..8276398f7d6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -66,12 +66,18 @@ struct mptcp_storage { static struct nstoken *create_netns(void) { - SYS(fail, "ip netns add %s", NS_TEST); - SYS(fail, "ip -net %s link set dev lo up", NS_TEST); + struct nstoken *nstoken; - return open_netns(NS_TEST); -fail: - return NULL; + if (make_netns(NS_TEST) < 0) + return NULL; + + nstoken = open_netns(NS_TEST); + if (!nstoken) { + log_err("open netns %s failed", NS_TEST); + remove_netns(NS_TEST); + } + + return nstoken; } static void cleanup_netns(struct nstoken *nstoken) @@ -79,7 +85,7 @@ static void cleanup_netns(struct nstoken *nstoken) if (nstoken) close_netns(nstoken); - SYS_NOFAIL("ip netns del %s", NS_TEST); + remove_netns(NS_TEST); } static int start_mptcp_server(int family, const char *addr_str, __u16 port, -- 2.45.2

1 year, 1 month

2
1
0 0

[PATCH 0/9] arm64: Support 2024 dpISA extensions

by Mark Brown

The 2024 architecture release includes a number of data processing extensions, mostly SVE and SME additions with a few others. These are all very straightforward extensions which add instructions but no architectural state so only need hwcaps and exposing of the ID registers to KVM guests and userspace. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (9): arm64/sysreg: Update ID_AA64PFR2_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR3_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64FPFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ZFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64SMFR0_EL1 to DDI0601 2024-09 arm64/sysreg: Update ID_AA64ISAR2_EL1 to DDI0601 2024-09 arm64/hwcap: Describe 2024 dpISA extensions to userspace KVM: arm64: Allow control of dpISA extensions in ID_AA64ISAR3_EL1 kselftest/arm64: Add 2024 dpISA extensions to hwcap test Documentation/arch/arm64/elf_hwcaps.rst | 51 ++++++ arch/arm64/include/asm/hwcap.h | 17 ++ arch/arm64/include/uapi/asm/hwcap.h | 17 ++ arch/arm64/kernel/cpufeature.c | 35 ++++ arch/arm64/kernel/cpuinfo.c | 17 ++ arch/arm64/kvm/sys_regs.c | 3 +- arch/arm64/tools/sysreg | 87 +++++++++- tools/testing/selftests/arm64/abi/hwcap.c | 273 +++++++++++++++++++++++++++++- 8 files changed, 490 insertions(+), 10 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241008-arm64-2024-dpisa-8091074a7f48 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

2
11
0 0

[PATCH v2] selftests: tc-testing: Fix typo error

by Karan Sanghavi

Correct the typo errors in json files - "diffferent" is corrected to "different". - "muliple" and "miltiple" is corrected to "multiple". Reviewed-by: Simon Horman <horms(a)kernel.org> Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Karan Sanghavi <karansanghvi98(a)gmail.com> --- Changes in v2: - Rewrote short log and commit message - Link to v1: https://lore.kernel.org/r/20241019-multiple_spell_error-v1-1-facff43b5610@g… --- tools/testing/selftests/tc-testing/tc-tests/filters/basic.json | 6 +++--- tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json | 6 +++--- tools/testing/selftests/tc-testing/tc-tests/filters/flow.json | 2 +- tools/testing/selftests/tc-testing/tc-tests/filters/route.json | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index d1278de8ebc3..c9309a44a87e 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -67,7 +67,7 @@ }, { "id": "4943", - "name": "Add basic filter with cmp ematch u32/link layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/link layer and multiple actions", "category": [ "filter", "basic" @@ -155,7 +155,7 @@ }, { "id": "32d8", - "name": "Add basic filter with cmp ematch u32/network layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/network layer and multiple actions", "category": [ "filter", "basic" @@ -243,7 +243,7 @@ }, { "id": "62d7", - "name": "Add basic filter with cmp ematch u32/transport layer and miltiple actions", + "name": "Add basic filter with cmp ematch u32/transport layer and multiple actions", "category": [ "filter", "basic" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json index 03723cf84379..35c9a7dbe1c4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/cgroup.json @@ -67,7 +67,7 @@ }, { "id": "0234", - "name": "Add cgroup filter with cmp ematch u32/link layer and miltiple actions", + "name": "Add cgroup filter with cmp ematch u32/link layer and multiple actions", "category": [ "filter", "cgroup" @@ -155,7 +155,7 @@ }, { "id": "2733", - "name": "Add cgroup filter with cmp ematch u32/network layer and miltiple actions", + "name": "Add cgroup filter with cmp ematch u32/network layer and multiple actions", "category": [ "filter", "cgroup" @@ -1189,7 +1189,7 @@ }, { "id": "4319", - "name": "Replace cgroup filter with diffferent match", + "name": "Replace cgroup filter with different match", "category": [ "filter", "cgroup" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 58189327f644..996448afe31b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -507,7 +507,7 @@ }, { "id": "4341", - "name": "Add flow filter with muliple ops", + "name": "Add flow filter with multiple ops", "category": [ "filter", "flow" diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json index 8d8de8f65aef..05cedca67cca 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/route.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/route.json @@ -111,7 +111,7 @@ }, { "id": "7994", - "name": "Add route filter with miltiple actions", + "name": "Add route filter with multiple actions", "category": [ "filter", "route" --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241017-multiple_spell_error-8b267ffffe47 Best regards, -- Karan Sanghavi <karansanghvi98(a)gmail.com>

1 year, 1 month

2
1
0 0

[PATCH 0/2] kselftest/arm64: fp-stress signal delivery interval improvements

by Mark Brown

One of the things that fp-stress does to stress the floating point context switching is send signals to the test threads it spawns. Currently we do this once per second but as suggested by Mark Rutland if we increase this we can improve the chances of triggering any issues with context switching the signal handling code. Do a quick change to increase the rate of signal delivery, trying to avoid excessive impact on emulated platforms, and a further change to mitigate the impact that this creates during startup. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (2): kselftest/arm64: Increase frequency of signal delivery in fp-stress kselftest/arm64: Lower poll interval while waiting for fp-stress children tools/testing/selftests/arm64/fp/fp-stress.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) --- base-commit: 8e929cb546ee42c9a61d24fae60605e9e3192354 change-id: 20241028-arm64-fp-stress-interval-8f5e62c06e12 Best regards, -- Mark Brown <broonie(a)kernel.org>

1 year, 1 month

2
5
0 0

[PATCH bpf-next v2] bpf: handle implicit declaration of function gettid in bpf_iter.c

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> As we can see from the title, when I compiled the selftests/bpf, I saw the error: implicit declaration of function ‘gettid’ ; did you mean ‘getgid’? [-Werror=implicit-function-declaration] skel->bss->tid = gettid(); ^~~~~~ getgid Directly call the syscall solves this issue. Signed-off-by: Jason Xing <kernelxing(a)tencent.com> --- v2 Link: https://lore.kernel.org/all/20241028034143.14675-1-kerneljasonxing@gmail.co… 1. directly call the syscall (Andrii) --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index f0a3a9c18e9e..9006549a1294 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -226,7 +226,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_OK(pthread_create(&thread_id, NULL, &do_nothing_wait, NULL), "pthread_create"); - skel->bss->tid = gettid(); + skel->bss->tid = syscall(SYS_gettid); do_dummy_read_opts(skel->progs.dump_task, opts); @@ -255,10 +255,10 @@ static void *run_test_task_tid(void *arg) union bpf_iter_link_info linfo; int num_unknown_tid, num_known_tid; - ASSERT_NEQ(getpid(), gettid(), "check_new_thread_id"); + ASSERT_NEQ(getpid(), syscall(SYS_gettid), "check_new_thread_id"); memset(&linfo, 0, sizeof(linfo)); - linfo.task.tid = gettid(); + linfo.task.tid = syscall(SYS_gettid); opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); test_task_common(&opts, 0, 1); -- 2.37.3

1 year, 1 month

3
2
0 0

[PATCH v4 0/5] implement lightweight guard pages

by Lorenzo Stoakes

Userland library functions such as allocators and threading implementations often require regions of memory to act as 'guard pages' - mappings which, when accessed, result in a fatal signal being sent to the accessing process. The current means by which these are implemented is via a PROT_NONE mmap() mapping, which provides the required semantics however incur an overhead of a VMA for each such region. With a great many processes and threads, this can rapidly add up and incur a significant memory penalty. It also has the added problem of preventing merges that might otherwise be permitted. This series takes a different approach - an idea suggested by Vlasimil Babka (and before him David Hildenbrand and Jann Horn - perhaps more - the provenance becomes a little tricky to ascertain after this - please forgive any omissions!) - rather than locating the guard pages at the VMA layer, instead placing them in page tables mapping the required ranges. Early testing of the prototype version of this code suggests a 5 times speed up in memory mapping invocations (in conjunction with use of process_madvise()) and a 13% reduction in VMAs on an entirely idle android system and unoptimised code. We expect with optimisation and a loaded system with a larger number of guard pages this could significantly increase, but in any case these numbers are encouraging. This way, rather than having separate VMAs specifying which parts of a range are guard pages, instead we have a VMA spanning the entire range of memory a user is permitted to access and including ranges which are to be 'guarded'. After mapping this, a user can specify which parts of the range should result in a fatal signal when accessed. By restricting the ability to specify guard pages to memory mapped by existing VMAs, we can rely on the mappings being torn down when the mappings are ultimately unmapped and everything works simply as if the memory were not faulted in, from the point of view of the containing VMAs. This mechanism in effect poisons memory ranges similar to hardware memory poisoning, only it is an entirely software-controlled form of poisoning. The mechanism is implemented via madvise() behaviour - MADV_GUARD_INSTALL which installs page table-level guard page markers - and MADV_GUARD_REMOVE - which clears them. Guard markers can be installed across multiple VMAs and any existing mappings will be cleared, that is zapped, before installing the guard page markers in the page tables. There is no concept of 'nested' guard markers, multiple attempts to install guard markers in a range will, after the first attempt, have no effect. Importantly, removing guard markers over a range that contains both guard markers and ordinary backed memory has no effect on anything but the guard markers (including leaving huge pages un-split), so a user can safely remove guard markers over a range of memory leaving the rest intact. The actual mechanism by which the page table entries are specified makes use of existing logic - PTE markers, which are used for the userfaultfd UFFDIO_POISON mechanism. Unfortunately PTE_MARKER_POISONED is not suited for the guard page mechanism as it results in VM_FAULT_HWPOISON semantics in the fault handler, so we add our own specific PTE_MARKER_GUARD and adapt existing logic to handle it. We also extend the generic page walk mechanism to allow for installation of PTEs (carefully restricted to memory management logic only to prevent unwanted abuse). We ensure that zapping performed by MADV_DONTNEED and MADV_FREE do not remove guard markers, nor does forking (except when VM_WIPEONFORK is specified for a VMA which implies a total removal of memory characteristics). It's important to note that the guard page implementation is emphatically NOT a security feature, so a user can remove the markers if they wish. We simply implement it in such a way as to provide the least surprising behaviour. An extensive set of self-tests are provided which ensure behaviour is as expected and additionally self-documents expected behaviour of guard ranges. Suggested-by: Vlastimil Babka <vbabka(a)suse.cz> Suggested-by: Jann Horn <jannh(a)google.com> Suggested-by: David Hildenbrand <david(a)redhat.com> v4 * Use restart_syscall() to implement -ERESTARTNOINTR to ensure correctly handled by kernel - tested this code path and confirmed it works correctly. Thanks to Vlastimil for pointing this issue out! * Updated the vector_madvise() handler to not unnecessarily invoke cond_resched() as suggested by Vlastimil. * Updated guard page tests to add a test for a vector operation which overwrites existing mappings. Tested this against the -ERESTARTNOINTR case and confirmed working. * Improved page walk logic further, refactoring handling logic as suggested by Vlastimil. * Moved MAX_MADVISE_GUARD_RETRIES to mm/madvise.c as suggested by Vlastimil. v3 * Cleaned up mm/pagewalk.c logic a bit to make things clearer, as suggested by Vlastiml. * Explicitly avoid splitting THP on PTE installation, as suggested by Vlastimil. Note this has no impact on the guard pages logic, which has page table entry handlers at PUD, PMD and PTE level. * Added WARN_ON_ONCE() to mm/hugetlb.c path where we don't expect a guard marker, as suggested by Vlastimil. * Reverted change to is_poisoned_swp_entry() to exclude guard pages which has the effect of MADV_FREE _not_ clearing guard pages. After discussion with Vlastimil, it became apparent that the ability to 'cancel' the freeing operation by writing to the mapping after having issued an MADV_FREE would mean that we would risk unexpected behaviour should the guard pages be removed, so we now do not remove markers here at all. * Added comment to PTE_MARKER_GUARD to highlight that memory tagged with the marker behaves as if it were a region mapped PROT_NONE, as highlighted by David. * Rename poison -> install, unpoison -> remove (i.e. MADV_GUARD_INSTALL / MADV_GUARD_REMOVE over MADV_GUARD_POISON / MADV_GUARD_REMOVE) at the request of David and John who both find the poison analogy confusing/overloaded. * After a lot of discussion, replace the looping behaviour should page faults race with guard page installation with a modest reattempt followed by returning -ERESTARTNOINTR to have the operation abort and re-enter, relieving lock contention and avoiding the possibility of allowing a malicious sandboxed process to impact the mmap lock or stall the overall process more than necessary, as suggested by Jann and Vlastimil having raised the issue. * Adjusted the page table walker so a populated huge PUD or PMD is correctly treated as being populated, necessitating a zap. In v2 we incorrectly skipped over these, which would cause the logic to wrongly proceed as if nothing were populated and the install succeeded. Instead, explicitly check to see if a huge page - if so, do not split but rather abort the operation and let zap take care of things. * Updated the guard remove logic to not unnecessarily split huge pages either. * Added a debug check to assert that the number of installed PTEs matches expectation, accounting for any existing guard pages. * Adapted vector_madvise() used by the process_madvise() system call to handle -ERESTARTNOINTR correctly. https://lore.kernel.org/all/cover.1729699916.git.lorenzo.stoakes@oracle.com/ v2 * The macros in kselftest_harness.h seem to be broken - __EXPECT() is terminated by '} while (0); OPTIONAL_HANDLER(_assert)' meaning it is not safe in single line if / else or for /which blocks, however working around this results in checkpatch producing invalid warnings, as reported by Shuah. * Fixing these macros is out of scope for this series, so compromise and instead rewrite test blocks so as to use multiple lines by separating out a decl in most cases. This has the side effect of, for the most part, making things more readable. * Heavily document the use of the volatile keyword - we can't avoid checkpatch complaining about this, so we explain it, as reported by Shuah. * Updated commit message to highlight that we skip tests we lack permissions for, as reported by Shuah. * Replaced a perror() with ksft_exit_fail_perror(), as reported by Shuah. * Added user friendly messages to cases where tests are skipped due to lack of permissions, as reported by Shuah. * Update the tool header to include the new MADV_GUARD_POISON/UNPOISON defines and directly include asm-generic/mman.h to get the platform-neutral versions to ensure we import them. * Finally fixed Vlastimil's email address in Suggested-by tags from suze to suse, as reported by Vlastimil. * Added linux-api to cc list, as reported by Vlastimil. https://lore.kernel.org/all/cover.1729440856.git.lorenzo.stoakes@oracle.com/ v1 * Un-RFC'd as appears no major objections to approach but rather debate on implementation. * Fixed issue with arches which need mmu_context.h and tlbfush.h. header imports in pagewalker logic to be able to use update_mmu_cache() as reported by the kernel test bot. * Added comments in page walker logic to clarify who can use ops->install_pte and why as well as adding a check_ops_valid() helper function, as suggested by Christoph. * Pass false in full parameter in pte_clear_not_present_full() as suggested by Jann. * Stopped erroneously requiring a write lock for the poison operation as suggested by Jann and Suren. * Moved anon_vma_prepare() to the start of madvise_guard_poison() to be consistent with how this is used elsewhere in the kernel as suggested by Jann. * Avoid returning -EAGAIN if we are raced on page faults, just keep looping and duck out if a fatal signal is pending or a conditional reschedule is needed, as suggested by Jann. * Avoid needlessly splitting huge PUDs and PMDs by specifying ACTION_CONTINUE, as suggested by Jann. https://lore.kernel.org/all/cover.1729196871.git.lorenzo.stoakes@oracle.com/ RFC https://lore.kernel.org/all/cover.1727440966.git.lorenzo.stoakes@oracle.com/ Lorenzo Stoakes (5): mm: pagewalk: add the ability to install PTEs mm: add PTE_MARKER_GUARD PTE marker mm: madvise: implement lightweight guard page mechanism tools: testing: update tools UAPI header for mman-common.h selftests/mm: add self tests for guard page feature arch/alpha/include/uapi/asm/mman.h | 3 + arch/mips/include/uapi/asm/mman.h | 3 + arch/parisc/include/uapi/asm/mman.h | 3 + arch/xtensa/include/uapi/asm/mman.h | 3 + include/linux/mm_inline.h | 2 +- include/linux/pagewalk.h | 18 +- include/linux/swapops.h | 24 +- include/uapi/asm-generic/mman-common.h | 3 + mm/hugetlb.c | 4 + mm/internal.h | 6 + mm/madvise.c | 239 ++++ mm/memory.c | 18 +- mm/mprotect.c | 6 +- mm/mseal.c | 1 + mm/pagewalk.c | 246 +++- tools/include/uapi/asm-generic/mman-common.h | 3 + tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/guard-pages.c | 1243 ++++++++++++++++++ 19 files changed, 1751 insertions(+), 76 deletions(-) create mode 100644 tools/testing/selftests/mm/guard-pages.c -- 2.47.0

1 year, 1 month

3
8
0 0

[PATCH net-next v10 00/23] Introducing OpenVPN Data Channel Offload

by Antonio Quartulli

Notable changes from v9: * fixed potential deadlock between peer float and keepalive worker * simplified skb CB layout to avoid allocating large mem area per pkt * fixed double free along encryption/decryption error path * fixed crash due to race condition in keepalive worker for p2p mode * mitigated race condition between TCP socket init and first strp rcv * added CMD_OVPN_KEY_GET doit handler (it went missing in v9) * removed double 'select STREAM_PARSER' in Kconfig * removed double include of socket.h in io.c * sorted new OVPN section in MAINTAINERS alphabetically * sorted F: entries in MAINTAINERS alphabetically * switched to state "Supported" in MAINTAINERS * added ending newline to various error messages in ovpn-cli.c * rearranged ovpn-cli.c for better readability and maintenance * ovpn-cli.c now compiles with -Wextra -Wall -pedantic * renamed selftest scripts * test-float.sh is now a stub that just calls test.sh with appropriate params Please note that patches previously reviewed by Andrew Lunn have retained the Reviewed-by tag as they have been simply rebased without major modifications. The latest code can also be found at: https://github.com/OpenVPN/linux-kernel-ovpn Thanks a lot! Best Regards, Antonio Quartulli OpenVPN Inc. --- Antonio Quartulli (23): netlink: add NLA_POLICY_MAX_LEN macro net: introduce OpenVPN Data Channel Offload (ovpn) ovpn: add basic netlink support ovpn: add basic interface creation/destruction/management routines ovpn: keep carrier always on ovpn: introduce the ovpn_peer object ovpn: introduce the ovpn_socket object ovpn: implement basic TX path (UDP) ovpn: implement basic RX path (UDP) ovpn: implement packet processing ovpn: store tunnel and transport statistics ovpn: implement TCP transport ovpn: implement multi-peer support ovpn: implement peer lookup logic ovpn: implement keepalive mechanism ovpn: add support for updating local UDP endpoint ovpn: add support for peer floating ovpn: implement peer add/get/dump/delete via netlink ovpn: implement key add/get/del/swap via netlink ovpn: kill key and notify userspace in case of IV exhaustion ovpn: notify userspace when a peer is deleted ovpn: add basic ethtool support testing/selftests: add test tool and scripts for ovpn module Documentation/netlink/specs/ovpn.yaml | 362 +++ MAINTAINERS | 11 + drivers/net/Kconfig | 14 + drivers/net/Makefile | 1 + drivers/net/ovpn/Makefile | 22 + drivers/net/ovpn/bind.c | 54 + drivers/net/ovpn/bind.h | 117 + drivers/net/ovpn/crypto.c | 214 ++ drivers/net/ovpn/crypto.h | 145 ++ drivers/net/ovpn/crypto_aead.c | 386 ++++ drivers/net/ovpn/crypto_aead.h | 33 + drivers/net/ovpn/io.c | 462 ++++ drivers/net/ovpn/io.h | 25 + drivers/net/ovpn/main.c | 337 +++ drivers/net/ovpn/main.h | 24 + drivers/net/ovpn/netlink-gen.c | 212 ++ drivers/net/ovpn/netlink-gen.h | 41 + drivers/net/ovpn/netlink.c | 1135 ++++++++++ drivers/net/ovpn/netlink.h | 18 + drivers/net/ovpn/ovpnstruct.h | 61 + drivers/net/ovpn/packet.h | 40 + drivers/net/ovpn/peer.c | 1201 ++++++++++ drivers/net/ovpn/peer.h | 165 ++ drivers/net/ovpn/pktid.c | 130 ++ drivers/net/ovpn/pktid.h | 87 + drivers/net/ovpn/proto.h | 104 + drivers/net/ovpn/skb.h | 56 + drivers/net/ovpn/socket.c | 178 ++ drivers/net/ovpn/socket.h | 55 + drivers/net/ovpn/stats.c | 21 + drivers/net/ovpn/stats.h | 47 + drivers/net/ovpn/tcp.c | 506 +++++ drivers/net/ovpn/tcp.h | 44 + drivers/net/ovpn/udp.c | 406 ++++ drivers/net/ovpn/udp.h | 26 + include/net/netlink.h | 1 + include/uapi/linux/if_link.h | 15 + include/uapi/linux/ovpn.h | 109 + include/uapi/linux/udp.h | 1 + tools/net/ynl/ynl-gen-c.py | 4 +- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/ovpn/.gitignore | 2 + tools/testing/selftests/net/ovpn/Makefile | 17 + tools/testing/selftests/net/ovpn/config | 10 + tools/testing/selftests/net/ovpn/data64.key | 5 + tools/testing/selftests/net/ovpn/ovpn-cli.c | 2370 ++++++++++++++++++++ tools/testing/selftests/net/ovpn/tcp_peers.txt | 5 + .../testing/selftests/net/ovpn/test-chachapoly.sh | 9 + tools/testing/selftests/net/ovpn/test-float.sh | 9 + tools/testing/selftests/net/ovpn/test-tcp.sh | 9 + tools/testing/selftests/net/ovpn/test.sh | 183 ++ tools/testing/selftests/net/ovpn/udp_peers.txt | 5 + 52 files changed, 9494 insertions(+), 1 deletion(-) --- base-commit: 03fc07a24735e0be8646563913abf5f5cb71ad19 change-id: 20241002-b4-ovpn-eeee35c694a2 Best regards, -- Antonio Quartulli <antonio(a)openvpn.net>

1 year, 1 month

4
30
0 0

[PATCH net-next 1/2] net: netconsole: selftests: Change the IP subnet

by Breno Leitao

Use a less populated IP range to run the tests, as suggested by Petr in Link: https://lore.kernel.org/netdev/87ikvukv3s.fsf@nvidia.com/. Suggested-by: Petr Machata <petrm(a)nvidia.com> Signed-off-by: Breno Leitao <leitao(a)debian.org> --- tools/testing/selftests/drivers/net/netcons_basic.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index 06021b2059b7..4ad1e216c6b0 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -20,9 +20,9 @@ SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") # Simple script to test dynamic targets in netconsole SRCIF="" # to be populated later -SRCIP=192.168.1.1 +SRCIP=192.168.2.1 DSTIF="" # to be populated later -DSTIP=192.168.1.2 +DSTIP=192.168.2.2 PORT="6666" MSG="netconsole selftest" -- 2.43.5

1 year, 1 month

2
3
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.12-rc3-8-gcecc795329fc)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.12-rc3-8-gcecc795329fc) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.12-rc3-8-gcec… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.12-rc3-8-gcecc795329fc URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: cecc795329fc3e0ea2e84567ee57570cc050cf6b Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/6720a2196a6ed469cec8688c Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-8-gcecc795329fc/arm/… HTML log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-8-gcecc795329fc/arm/… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/6720a2196a6ed469cec8688d failing since 91 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 1 month

1
0
0 0

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.12-rc3-8-gcecc795329fc)

by kernelci.org bot

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.12-rc3-8-gcecc795329fc) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.12-rc3-8-gcec… Test: kselftest-lib Tree: kselftest Branch: next Describe: v6.12-rc3-8-gcecc795329fc URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: cecc795329fc3e0ea2e84567ee57570cc050cf6b Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/6720a485c2f02871e7c86857 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-8-gcecc795329fc/arm/… HTML log: https://storage.kernelci.org//kselftest/next/v6.12-rc3-8-gcecc795329fc/arm/… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lib.login: https://kernelci.org/test/case/id/6720a485c2f02871e7c86858 failing since 91 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

1 year, 1 month

1
0
0 0

[PATCH net-next v2 2/2] net: netconsole: selftests: Add userdata validation

by Breno Leitao

Extend netcons_basic selftest to verify the userdata functionality by: 1. Creating a test key in the userdata configfs directory 2. Writing a known value to the key 3. Validating the key-value pair appears in the captured network output This ensures the userdata feature is properly tested during selftests. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- .../selftests/drivers/net/netcons_basic.sh | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index 8d28e5189e91..182eb1a97e59 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -26,10 +26,13 @@ DSTIP=192.0.2.2 PORT="6666" MSG="netconsole selftest" +USERDATA_KEY="key" +USERDATA_VALUE="value" TARGET=$(mktemp -u netcons_XXXXX) DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) NETCONS_CONFIGFS="/sys/kernel/config/netconsole" NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" # NAMESPACE will be populated by setup_ns with a random value NAMESPACE="" @@ -122,6 +125,8 @@ function cleanup() { # delete netconsole dynamic reconfiguration echo 0 > "${NETCONS_PATH}"/enabled + # Remove key + rmdir "${KEY_PATH}" # Remove the configfs entry rmdir "${NETCONS_PATH}" @@ -136,6 +141,18 @@ function cleanup() { echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk } +function set_user_data() { + if [[ ! -d "${NETCONS_PATH}""/userdata" ]] + then + echo "Userdata path not available in ${NETCONS_PATH}/userdata" + exit "${ksft_skip}" + fi + + mkdir -p "${KEY_PATH}" + VALUE_PATH="${KEY_PATH}""/value" + echo "${USERDATA_VALUE}" > "${VALUE_PATH}" +} + function listen_port_and_save_to() { local OUTPUT=${1} # Just wait for 2 seconds @@ -146,6 +163,10 @@ function listen_port_and_save_to() { function validate_result() { local TMPFILENAME="$1" + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + # Check if the file exists if [ ! -f "$TMPFILENAME" ]; then echo "FAIL: File was not generated." >&2 @@ -158,6 +179,12 @@ function validate_result() { exit "${ksft_fail}" fi + if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then + echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + # Delete the file once it is validated, otherwise keep it # for debugging purposes rm "${TMPFILENAME}" @@ -220,6 +247,8 @@ trap cleanup EXIT set_network # Create a dynamic target for netconsole create_dynamic_target +# Set userdata "key" with the "value" value +set_user_data # Listed for netconsole port inside the namespace and destination interface listen_port_and_save_to "${OUTPUT_FILE}" & # Wait for socat to start and listen to the port. -- 2.43.5

1 year, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror