mirror of
https://github.com/torvalds/linux.git
synced 2024-11-13 15:41:39 +00:00
5ddf994fa2
"Ma, XinjianX" <xinjianx.ma@intel.com> reported:
> When lkp team run kernel selftests, we found after these series of patches, testcase mqueue: mq_perf_tests
> in kselftest failed with following message.
>
> # selftests: mqueue: mq_perf_tests
> #
> # Initial system state:
> # Using queue path: /mq_perf_tests
> # RLIMIT_MSGQUEUE(soft): 819200
> # RLIMIT_MSGQUEUE(hard): 819200
> # Maximum Message Size: 8192
> # Maximum Queue Size: 10
> # Nice value: 0
> #
> # Adjusted system state for testing:
> # RLIMIT_MSGQUEUE(soft): (unlimited)
> # RLIMIT_MSGQUEUE(hard): (unlimited)
> # Maximum Message Size: 16777216
> # Maximum Queue Size: 65530
> # Nice value: -20
> # Continuous mode: (disabled)
> # CPUs to pin: 3
> # ./mq_perf_tests: mq_open() at 296: Too many open files
> not ok 2 selftests: mqueue: mq_perf_tests # exit=1
> ```
>
> Test env:
> rootfs: debian-10
> gcc version: 9
After investigation the problem turned out to be that ucount_max for
the rlimits in init_user_ns was being set to the initial rlimit value.
The practical problem is that ucount_max provides a limit that
applications inside the user namespace can not exceed. Which means in
practice that rlimits that have been converted to use the ucount
infrastructure were not able to exceend their initial rlimits.
Solve this by setting the relevant values of ucount_max to
RLIM_INIFINITY. A limit in init_user_ns is pointless so the code
should allow the values to grow as large as possible without riscking
an underflow or an overflow.
As the ltp test case was a bit of a pain I have reproduced the rlimit failure
and tested the fix with the following little C program:
> #include <stdio.h>
> #include <fcntl.h>
> #include <sys/stat.h>
> #include <mqueue.h>
> #include <sys/time.h>
> #include <sys/resource.h>
> #include <errno.h>
> #include <string.h>
> #include <stdlib.h>
> #include <limits.h>
> #include <unistd.h>
>
> int main(int argc, char **argv)
> {
> struct mq_attr mq_attr;
> struct rlimit rlim;
> mqd_t mqd;
> int ret;
>
> ret = getrlimit(RLIMIT_MSGQUEUE, &rlim);
> if (ret != 0) {
> fprintf(stderr, "getrlimit(RLIMIT_MSGQUEUE) failed: %s\n", strerror(errno));
> exit(EXIT_FAILURE);
> }
> printf("RLIMIT_MSGQUEUE %lu %lu\n",
> rlim.rlim_cur, rlim.rlim_max);
> rlim.rlim_cur = RLIM_INFINITY;
> rlim.rlim_max = RLIM_INFINITY;
> ret = setrlimit(RLIMIT_MSGQUEUE, &rlim);
> if (ret != 0) {
> fprintf(stderr, "setrlimit(RLIMIT_MSGQUEUE, RLIM_INFINITY) failed: %s\n", strerror(errno));
> exit(EXIT_FAILURE);
> }
>
> memset(&mq_attr, 0, sizeof(struct mq_attr));
> mq_attr.mq_maxmsg = 65536 - 1;
> mq_attr.mq_msgsize = 16*1024*1024 - 1;
>
> mqd = mq_open("/mq_rlimit_test", O_RDONLY|O_CREAT, 0600, &mq_attr);
> if (mqd == (mqd_t)-1) {
> fprintf(stderr, "mq_open failed: %s\n", strerror(errno));
> exit(EXIT_FAILURE);
> }
> ret = mq_close(mqd);
> if (ret) {
> fprintf(stderr, "mq_close failed; %s\n", strerror(errno));
> exit(EXIT_FAILURE);
> }
>
> return EXIT_SUCCESS;
> }
Fixes:
|
||
|---|---|---|
| .. | ||
| bpf | ||
| cgroup | ||
| configs | ||
| debug | ||
| dma | ||
| entry | ||
| events | ||
| gcov | ||
| irq | ||
| kcsan | ||
| livepatch | ||
| locking | ||
| power | ||
| printk | ||
| rcu | ||
| sched | ||
| time | ||
| trace | ||
| .gitignore | ||
| acct.c | ||
| async.c | ||
| audit_fsnotify.c | ||
| audit_tree.c | ||
| audit_watch.c | ||
| audit.c | ||
| audit.h | ||
| auditfilter.c | ||
| auditsc.c | ||
| backtracetest.c | ||
| bounds.c | ||
| capability.c | ||
| cfi.c | ||
| compat.c | ||
| configs.c | ||
| context_tracking.c | ||
| cpu_pm.c | ||
| cpu.c | ||
| crash_core.c | ||
| crash_dump.c | ||
| cred.c | ||
| delayacct.c | ||
| dma.c | ||
| exec_domain.c | ||
| exit.c | ||
| extable.c | ||
| fail_function.c | ||
| fork.c | ||
| freezer.c | ||
| futex.c | ||
| gen_kheaders.sh | ||
| groups.c | ||
| hung_task.c | ||
| iomem.c | ||
| irq_work.c | ||
| jump_label.c | ||
| kallsyms.c | ||
| kcmp.c | ||
| Kconfig.freezer | ||
| Kconfig.hz | ||
| Kconfig.locks | ||
| Kconfig.preempt | ||
| kcov.c | ||
| kexec_core.c | ||
| kexec_elf.c | ||
| kexec_file.c | ||
| kexec_internal.h | ||
| kexec.c | ||
| kheaders.c | ||
| kmod.c | ||
| kprobes.c | ||
| ksysfs.c | ||
| kthread.c | ||
| latencytop.c | ||
| Makefile | ||
| module_signature.c | ||
| module_signing.c | ||
| module-internal.h | ||
| module.c | ||
| notifier.c | ||
| nsproxy.c | ||
| padata.c | ||
| panic.c | ||
| params.c | ||
| pid_namespace.c | ||
| pid.c | ||
| profile.c | ||
| ptrace.c | ||
| range.c | ||
| reboot.c | ||
| regset.c | ||
| relay.c | ||
| resource_kunit.c | ||
| resource.c | ||
| rseq.c | ||
| scftorture.c | ||
| scs.c | ||
| seccomp.c | ||
| signal.c | ||
| smp.c | ||
| smpboot.c | ||
| smpboot.h | ||
| softirq.c | ||
| stackleak.c | ||
| stacktrace.c | ||
| static_call.c | ||
| stop_machine.c | ||
| sys_ni.c | ||
| sys.c | ||
| sysctl-test.c | ||
| sysctl.c | ||
| task_work.c | ||
| taskstats.c | ||
| test_kprobes.c | ||
| torture.c | ||
| tracepoint.c | ||
| tsacct.c | ||
| ucount.c | ||
| uid16.c | ||
| uid16.h | ||
| umh.c | ||
| up.c | ||
| user_namespace.c | ||
| user-return-notifier.c | ||
| user.c | ||
| usermode_driver.c | ||
| utsname_sysctl.c | ||
| utsname.c | ||
| watch_queue.c | ||
| watchdog_hld.c | ||
| watchdog.c | ||
| workqueue_internal.h | ||
| workqueue.c | ||