| Message ID | 20220518204316.13131-1-surenb@google.com |
|---|---|
| State | Accepted |
| Commit | 33776141b81296e604a39a8065b28b89c61c7f74 |
| Headers | show |
| Series | [v3,1/1] selftests: vm: add process_mrelease tests | expand |
On 5/18/22 2:43 PM, Suren Baghdasaryan wrote: > Introduce process_mrelease syscall sanity tests which include tests > which expect to fail: > - process_mrelease with invalid pidfd and flags inputs > - process_mrelease on a live process with no pending signals > and valid process_mrelease usage which is expected to succeed. > Because process_mrelease has to be used against a process with a pending > SIGKILL, it's possible that the process exits before process_mrelease > gets called. In such cases we retry the test with a victim that allocates > twice more memory up to 1GB. This would require the victim process to > spend more time during exit and process_mrelease has a better chance of > catching the process before it exits and succeeding. > > On success the test reports the amount of memory the child had to > allocate for reaping to succeed. Sample output: > > $ mrelease_test > Success reaping a child with 1MB of memory allocations > > On failure the test reports the failure. Sample outputs: > > $ mrelease_test > All process_mrelease attempts failed! > > $ mrelease_test > process_mrelease: Invalid argument > > Signed-off-by: Suren Baghdasaryan <surenb@google.com> > --- > Changes in v3: > - Applied on git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm mm-stable, > per Andrew > - Fixed formatting for sample outputs in the description, per Shuah > - Removed pidfd_open, process_mrelease, write_fault_pages functions, per Shuah > - Moved child main routine into its own function, per Shuah > - Followed tools/testing/selftests/pidfd/pidfd.h as a model to deal with > undefined syscall numbers, per Shuah > Looks good to me Suren. Thank you. Reviewed-by: Shuah Khan <skhan@linuxfoundation.org> thanks, -- Shuah
On Wed, May 18, 2022 at 01:43:16PM -0700, Suren Baghdasaryan wrote: > Introduce process_mrelease syscall sanity tests which include tests > which expect to fail: > - process_mrelease with invalid pidfd and flags inputs > - process_mrelease on a live process with no pending signals > and valid process_mrelease usage which is expected to succeed. > Because process_mrelease has to be used against a process with a pending > SIGKILL, it's possible that the process exits before process_mrelease > gets called. In such cases we retry the test with a victim that allocates > twice more memory up to 1GB. This would require the victim process to > spend more time during exit and process_mrelease has a better chance of > catching the process before it exits and succeeding. > > On success the test reports the amount of memory the child had to > allocate for reaping to succeed. Sample output: > > $ mrelease_test > Success reaping a child with 1MB of memory allocations > > On failure the test reports the failure. Sample outputs: > > $ mrelease_test > All process_mrelease attempts failed! > > $ mrelease_test > process_mrelease: Invalid argument > > Signed-off-by: Suren Baghdasaryan <surenb@google.com> > --- Thanks your adding selftests, Suren! Acked-by: Christian Brauner (Microsoft) <brauner@kernel.org>
On 5/19/22 1:43 AM, Suren Baghdasaryan wrote: > Introduce process_mrelease syscall sanity tests which include tests > which expect to fail: > - process_mrelease with invalid pidfd and flags inputs > - process_mrelease on a live process with no pending signals > and valid process_mrelease usage which is expected to succeed. > Because process_mrelease has to be used against a process with a pending > SIGKILL, it's possible that the process exits before process_mrelease > gets called. In such cases we retry the test with a victim that allocates > twice more memory up to 1GB. This would require the victim process to > spend more time during exit and process_mrelease has a better chance of > catching the process before it exits and succeeding. > > On success the test reports the amount of memory the child had to > allocate for reaping to succeed. Sample output: > > $ mrelease_test > Success reaping a child with 1MB of memory allocations > > On failure the test reports the failure. Sample outputs: > > $ mrelease_test > All process_mrelease attempts failed! > > $ mrelease_test > process_mrelease: Invalid argument > > Signed-off-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 3cb4fa771ec2..6c2ac4208c27 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -10,6 +10,7 @@ map_populate thuge-gen compaction_test mlock2-tests +mrelease_test mremap_dontunmap mremap_test on-fault-limit diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index f1228370e99b..8111a33e4824 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -44,6 +44,7 @@ TEST_GEN_FILES += memfd_secret TEST_GEN_FILES += migration TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += on-fault-limit diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/vm/mrelease_test.c new file mode 100644 index 000000000000..96671c2f7d48 --- /dev/null +++ b/tools/testing/selftests/vm/mrelease_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2022 Google LLC + */ +#define _GNU_SOURCE +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "util.h" + +#include "../kselftest.h" + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +#ifndef __NR_process_mrelease +#define __NR_process_mrelease -1 +#endif + +#define MB(x) (x << 20) +#define MAX_SIZE_MB 1024 + +static int alloc_noexit(unsigned long nr_pages, int pipefd) +{ + int ppid = getppid(); + int timeout = 10; /* 10sec timeout to get killed */ + unsigned long i; + char *buf; + + buf = (char *)mmap(NULL, nr_pages * PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, 0, 0); + if (buf == MAP_FAILED) { + perror("mmap failed, halting the test"); + return KSFT_FAIL; + } + + for (i = 0; i < nr_pages; i++) + *((unsigned long *)(buf + (i * PAGE_SIZE))) = i; + + /* Signal the parent that the child is ready */ + if (write(pipefd, "", 1) < 0) { + perror("write"); + return KSFT_FAIL; + } + + /* Wait to be killed (when reparenting happens) */ + while (getppid() == ppid && timeout > 0) { + sleep(1); + timeout--; + } + + munmap(buf, nr_pages * PAGE_SIZE); + + return (timeout > 0) ? KSFT_PASS : KSFT_FAIL; +} + +/* The process_mrelease calls in this test are expected to fail */ +static void run_negative_tests(int pidfd) +{ + /* Test invalid flags. Expect to fail with EINVAL error code. */ + if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || + errno != EINVAL) { + perror("process_mrelease with wrong flags"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + /* + * Test reaping while process is alive with no pending SIGKILL. + * Expect to fail with EINVAL error code. + */ + if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { + perror("process_mrelease on a live process"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } +} + +static int child_main(int pipefd[], size_t size) +{ + int res; + + /* Allocate and fault-in memory and wait to be killed */ + close(pipefd[0]); + res = alloc_noexit(MB(size) / PAGE_SIZE, pipefd[1]); + close(pipefd[1]); + return res; +} + +int main(void) +{ + int pipefd[2], pidfd; + bool success, retry; + size_t size; + pid_t pid; + char byte; + int res; + + /* Test a wrong pidfd */ + if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { + perror("process_mrelease with wrong pidfd"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + + /* Start the test with 1MB child memory allocation */ + size = 1; +retry: + /* + * Pipe for the child to signal when it's done allocating + * memory + */ + if (pipe(pipefd)) { + perror("pipe"); + exit(KSFT_FAIL); + } + pid = fork(); + if (pid < 0) { + perror("fork"); + close(pipefd[0]); + close(pipefd[1]); + exit(KSFT_FAIL); + } + + if (pid == 0) { + /* Child main routine */ + res = child_main(pipefd, size); + exit(res); + } + + /* + * Parent main routine: + * Wait for the child to finish allocations, then kill and reap + */ + close(pipefd[1]); + /* Block until the child is ready */ + res = read(pipefd[0], &byte, 1); + close(pipefd[0]); + if (res < 0) { + perror("read"); + if (!kill(pid, SIGKILL)) + waitpid(pid, NULL, 0); + exit(KSFT_FAIL); + } + + pidfd = syscall(__NR_pidfd_open, pid, 0); + if (pidfd < 0) { + perror("pidfd_open"); + if (!kill(pid, SIGKILL)) + waitpid(pid, NULL, 0); + exit(KSFT_FAIL); + } + + /* Run negative tests which require a live child */ + run_negative_tests(pidfd); + + if (kill(pid, SIGKILL)) { + perror("kill"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + + success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); + if (!success) { + /* + * If we failed to reap because the child exited too soon, + * before we could call process_mrelease. Double child's memory + * which causes it to spend more time on cleanup and increases + * our chances of reaping its memory before it exits. + * Retry until we succeed or reach MAX_SIZE_MB. + */ + if (errno == ESRCH) { + retry = (size <= MAX_SIZE_MB); + } else { + perror("process_mrelease"); + waitpid(pid, NULL, 0); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + } + + /* Cleanup to prevent zombies */ + if (waitpid(pid, NULL, 0) < 0) { + perror("waitpid"); + exit(KSFT_FAIL); + } + close(pidfd); + + if (!success) { + if (retry) { + size *= 2; + goto retry; + } + printf("All process_mrelease attempts failed!\n"); + exit(KSFT_FAIL); + } + + printf("Success reaping a child with %zuMB of memory allocations\n", + size); + return KSFT_PASS; +} diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index a2302b5faaf2..41fce8bea929 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -141,6 +141,8 @@ run_test ./mlock-random-test run_test ./mlock2-tests +run_test ./mrelease_test + run_test ./mremap_test run_test ./thuge-gen
Introduce process_mrelease syscall sanity tests which include tests which expect to fail: - process_mrelease with invalid pidfd and flags inputs - process_mrelease on a live process with no pending signals and valid process_mrelease usage which is expected to succeed. Because process_mrelease has to be used against a process with a pending SIGKILL, it's possible that the process exits before process_mrelease gets called. In such cases we retry the test with a victim that allocates twice more memory up to 1GB. This would require the victim process to spend more time during exit and process_mrelease has a better chance of catching the process before it exits and succeeding. On success the test reports the amount of memory the child had to allocate for reaping to succeed. Sample output: $ mrelease_test Success reaping a child with 1MB of memory allocations On failure the test reports the failure. Sample outputs: $ mrelease_test All process_mrelease attempts failed! $ mrelease_test process_mrelease: Invalid argument Signed-off-by: Suren Baghdasaryan <surenb@google.com> --- Changes in v3: - Applied on git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm mm-stable, per Andrew - Fixed formatting for sample outputs in the description, per Shuah - Removed pidfd_open, process_mrelease, write_fault_pages functions, per Shuah - Moved child main routine into its own function, per Shuah - Followed tools/testing/selftests/pidfd/pidfd.h as a model to deal with undefined syscall numbers, per Shuah tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/vm/mrelease_test.c | 200 +++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests.sh | 2 + 4 files changed, 204 insertions(+) create mode 100644 tools/testing/selftests/vm/mrelease_test.c