From 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d Mon Sep 17 00:00:00 2001 From: Zeng Chi Date: Mon, 21 Sep 2026 18:24:42 +0800 Subject: KVM: Don't pre-reserve xarray entries when storing empty/NULL attributes Skip the xarray reservation loop when clearing all memory attributes, as storing NULL only erases the entry and never needs to allocate, so no reservation (and no cleanup of a failed one) is required in that case. Suggested-by: Sean Christopherson Cc: David Ballesteros Signed-off-by: Zeng Chi Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com [sean: split to separate patch] Signed-off-by: Sean Christopherson --- tools/testing/selftests/rlimits/.gitignore | 2 + tools/testing/selftests/rlimits/Makefile | 6 + tools/testing/selftests/rlimits/config | 1 + .../testing/selftests/rlimits/rlimits-per-userns.c | 161 +++++++++++++++++++++ 4 files changed, 170 insertions(+) create mode 100644 tools/testing/selftests/rlimits/.gitignore create mode 100644 tools/testing/selftests/rlimits/Makefile create mode 100644 tools/testing/selftests/rlimits/config create mode 100644 tools/testing/selftests/rlimits/rlimits-per-userns.c (limited to 'tools/testing/selftests/rlimits') diff --git a/tools/testing/selftests/rlimits/.gitignore b/tools/testing/selftests/rlimits/.gitignore new file mode 100644 index 000000000..091021f25 --- /dev/null +++ b/tools/testing/selftests/rlimits/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +rlimits-per-userns diff --git a/tools/testing/selftests/rlimits/Makefile b/tools/testing/selftests/rlimits/Makefile new file mode 100644 index 000000000..03aadb406 --- /dev/null +++ b/tools/testing/selftests/rlimits/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g +TEST_GEN_PROGS := rlimits-per-userns + +include ../lib.mk diff --git a/tools/testing/selftests/rlimits/config b/tools/testing/selftests/rlimits/config new file mode 100644 index 000000000..416bd53ce --- /dev/null +++ b/tools/testing/selftests/rlimits/config @@ -0,0 +1 @@ +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/rlimits/rlimits-per-userns.c b/tools/testing/selftests/rlimits/rlimits-per-userns.c new file mode 100644 index 000000000..26dc949e9 --- /dev/null +++ b/tools/testing/selftests/rlimits/rlimits-per-userns.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Alexey Gladkov + */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define NR_CHILDS 2 + +static char *service_prog; +static uid_t user = 60000; +static uid_t group = 60000; + +static void setrlimit_nproc(rlim_t n) +{ + pid_t pid = getpid(); + struct rlimit limit = { + .rlim_cur = n, + .rlim_max = n + }; + + warnx("(pid=%d): Setting RLIMIT_NPROC=%ld", pid, n); + + if (setrlimit(RLIMIT_NPROC, &limit) < 0) + err(EXIT_FAILURE, "(pid=%d): setrlimit(RLIMIT_NPROC)", pid); +} + +static pid_t fork_child(void) +{ + pid_t pid = fork(); + + if (pid < 0) + err(EXIT_FAILURE, "fork"); + + if (pid > 0) + return pid; + + pid = getpid(); + + warnx("(pid=%d): New process starting ...", pid); + + if (prctl(PR_SET_PDEATHSIG, SIGKILL) < 0) + err(EXIT_FAILURE, "(pid=%d): prctl(PR_SET_PDEATHSIG)", pid); + + signal(SIGUSR1, SIG_DFL); + + warnx("(pid=%d): Changing to uid=%d, gid=%d", pid, user, group); + + if (setgid(group) < 0) + err(EXIT_FAILURE, "(pid=%d): setgid(%d)", pid, group); + if (setuid(user) < 0) + err(EXIT_FAILURE, "(pid=%d): setuid(%d)", pid, user); + + warnx("(pid=%d): Service running ...", pid); + + warnx("(pid=%d): Unshare user namespace", pid); + if (unshare(CLONE_NEWUSER) < 0) + err(EXIT_FAILURE, "unshare(CLONE_NEWUSER)"); + + char *const argv[] = { "service", NULL }; + char *const envp[] = { "I_AM_SERVICE=1", NULL }; + + warnx("(pid=%d): Executing real service ...", pid); + + execve(service_prog, argv, envp); + err(EXIT_FAILURE, "(pid=%d): execve", pid); +} + +int main(int argc, char **argv) +{ + size_t i; + pid_t child[NR_CHILDS]; + int wstatus[NR_CHILDS]; + int childs = NR_CHILDS; + pid_t pid; + + if (getenv("I_AM_SERVICE")) { + pause(); + exit(EXIT_SUCCESS); + } + + service_prog = argv[0]; + pid = getpid(); + + warnx("(pid=%d) Starting testcase", pid); + + /* + * This rlimit is not a problem for root because it can be exceeded. + */ + setrlimit_nproc(1); + + for (i = 0; i < NR_CHILDS; i++) { + child[i] = fork_child(); + wstatus[i] = 0; + usleep(250000); + } + + while (1) { + for (i = 0; i < NR_CHILDS; i++) { + if (child[i] <= 0) + continue; + + errno = 0; + pid_t ret = waitpid(child[i], &wstatus[i], WNOHANG); + + if (!ret || (!WIFEXITED(wstatus[i]) && !WIFSIGNALED(wstatus[i]))) + continue; + + if (ret < 0 && errno != ECHILD) + warn("(pid=%d): waitpid(%d)", pid, child[i]); + + child[i] *= -1; + childs -= 1; + } + + if (!childs) + break; + + usleep(250000); + + for (i = 0; i < NR_CHILDS; i++) { + if (child[i] <= 0) + continue; + kill(child[i], SIGUSR1); + } + } + + for (i = 0; i < NR_CHILDS; i++) { + if (WIFEXITED(wstatus[i])) + warnx("(pid=%d): pid %d exited, status=%d", + pid, -child[i], WEXITSTATUS(wstatus[i])); + else if (WIFSIGNALED(wstatus[i])) + warnx("(pid=%d): pid %d killed by signal %d", + pid, -child[i], WTERMSIG(wstatus[i])); + + if (WIFSIGNALED(wstatus[i]) && WTERMSIG(wstatus[i]) == SIGUSR1) + continue; + + warnx("(pid=%d): Test failed", pid); + exit(EXIT_FAILURE); + } + + warnx("(pid=%d): Test passed", pid); + exit(EXIT_SUCCESS); +} -- cgit v1.3.1