Create ASSERT_{EQ, NE, TRUE, FALSE} macros to make test creation easier.

Signed-off-by: André Almeida andrealmeid@igalia.com --- tools/testing/selftests/futex/include/logging.h | 38 +++++++++++++++++++++++++ 1 file changed, 38 insertions(+)

diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h index 874c69ce5cce9efa3a9d6de246f5972a75437dbf..a19755622a877932884570c8f58aaee7371d5f8f 100644 --- a/tools/testing/selftests/futex/include/logging.h +++ b/tools/testing/selftests/futex/include/logging.h @@ -23,6 +23,44 @@ #include <linux/futex.h> #include "kselftest.h"

+#define ASSERT_EQ(var, value) \ +do { \ + if (var != value) { \ + ksft_test_result_fail("%s: expected %ld, but %s has %ld\n", \ + __func__, (long) value, #var, \ + (long) var); \ + return; \ + } \ +} while (0) + +#define ASSERT_NE(var, value) \ +do { \ + if (var == value) { \ + ksft_test_result_fail("%s: expected not %ld, but %s has %ld\n", \ + __func__, (long) value, #var, \ + (long) var); \ + return; \ + } \ +} while (0) + +#define ASSERT_TRUE(var) \ +do { \ + if ((var) == 0) { \ + ksft_test_result_fail("%s: expected %s to be true\n", \ + __func__, #var); \ + return; \ + } \ +} while (0) + +#define ASSERT_FALSE(var) \ +do { \ + if (var) { \ + ksft_test_result_fail("%s: expected %s to be false\n", \ + __func__, #var); \ + return; \ + } \ +} while (0) + /* * Define PASS, ERROR, and FAIL strings with and without color escape * sequences, default to no color.

Create a test for the robust list mechanism. Test the following uAPI operations:

- Creating a robust mutex where the lock waiter is wake by the kernel when the lock owner died - Setting a robust list to the current task - Getting a robust list from the current task - Getting a robust list from another task - Using the list_op_pending field from robust_list_head struct to test robustness when the lock owner dies before completing the locking - Setting a invalid size for syscall argument `len` - Adding multiple elements to a robust list wait waiting for each of them - Creating a circular list and checking that the kernel does not get stuck in an infinity loop

This is the expected output:

TAP version 13 1..7 ok 1 test_robustness ok 2 test_set_robust_list_invalid_size ok 3 test_get_robust_list_self ok 4 test_get_robust_list_child ok 5 test_set_list_op_pending ok 6 test_robust_list_multiple_elements ok 7 test_circular_list # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: André Almeida andrealmeid@igalia.com --- .../testing/selftests/futex/functional/.gitignore | 1 + tools/testing/selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 554 +++++++++++++++++++++ 3 files changed, 557 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 7b24ae89594a9db211d4b8469ebcef8d1f7012d8..7f447ebfbc62bbad9add0dc86a75abcdb8a4d9a7 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -11,3 +11,4 @@ futex_wait_timeout futex_wait_uninitialized_heap futex_wait_wouldblock futex_waitv +robust_list diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 8cfb87f7f7c5059c82f1e6290c076d3f13f5ea41..e6fa66e622dee4de74c31c8b9b486ca01de35737 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -20,7 +20,8 @@ TEST_GEN_PROGS := \ futex_priv_hash \ futex_numa_mpol \ futex_waitv \ - futex_numa + futex_numa \ + robust_list

TEST_PROGS := run.sh

diff --git a/tools/testing/selftests/futex/functional/robust_list.c b/tools/testing/selftests/futex/functional/robust_list.c new file mode 100644 index 0000000000000000000000000000000000000000..42690b2440fd29a9b12c46f67f9645ccc93d1147 --- /dev/null +++ b/tools/testing/selftests/futex/functional/robust_list.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2024 Igalia S.L. + * + * Robust list test by André Almeida andrealmeid@igalia.com + * + * The robust list uAPI allows userspace to create "robust" locks, in the sense + * that if the lock holder thread dies, the remaining threads that are waiting + * for the lock won't block forever, waiting for a lock that will never be + * released. + * + * This is achieve by userspace setting a list where a thread can enter all the + * locks (futexes) that it is holding. The robust list is a linked list, and + * userspace register the start of the list with the syscall set_robust_list(). + * If such thread eventually dies, the kernel will walk this list, waking up one + * thread waiting for each futex and marking the futex word with the flag + * FUTEX_OWNER_DIED. + * + * See also + * man set_robust_list + * Documententation/locking/robust-futex-ABI.rst + * Documententation/locking/robust-futexes.rst + */ + +#define _GNU_SOURCE + +#include "futextest.h" +#include "logging.h" + +#include <errno.h> +#include <pthread.h> +#include <signal.h> +#include <stdatomic.h> +#include <stdbool.h> +#include <stddef.h> +#include <sys/mman.h> +#include <sys/wait.h> + +#define STACK_SIZE (1024 * 1024) + +#define FUTEX_TIMEOUT 3 + +static pthread_barrier_t barrier, barrier2; + +int set_robust_list(struct robust_list_head *head, size_t len) +{ + return syscall(SYS_set_robust_list, head, len); +} + +int get_robust_list(int pid, struct robust_list_head **head, size_t *len_ptr) +{ + return syscall(SYS_get_robust_list, pid, head, len_ptr); +} + +/* + * Basic lock struct, contains just the futex word and the robust list element + * Real implementations have also a *prev to easily walk in the list + */ +struct lock_struct { + _Atomic(unsigned int) futex; + struct robust_list list; +}; + +/* + * Helper function to spawn a child thread. Returns -1 on error, pid on success + */ +static int create_child(int (*fn)(void *arg), void *arg) +{ + char *stack; + pid_t pid; + + stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (stack == MAP_FAILED) + return -1; + + stack += STACK_SIZE; + + pid = clone(fn, stack, CLONE_VM | SIGCHLD, arg); + + if (pid == -1) + return -1; + + return pid; +} + +/* + * Helper function to prepare and register a robust list + */ +static int set_list(struct robust_list_head *head) +{ + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + return ret; + + head->futex_offset = (size_t) offsetof(struct lock_struct, futex) - + (size_t) offsetof(struct lock_struct, list); + head->list.next = &head->list; + head->list_op_pending = NULL; + + return 0; +} + +/* + * A basic (and incomplete) mutex lock function with robustness + */ +static int mutex_lock(struct lock_struct *lock, struct robust_list_head *head, bool error_inject) +{ + _Atomic(unsigned int) *futex = &lock->futex; + unsigned int zero = 0; + int ret = -1; + pid_t tid = gettid(); + + /* + * Set list_op_pending before starting the lock, so the kernel can catch + * the case where the thread died during the lock operation + */ + head->list_op_pending = &lock->list; + + if (atomic_compare_exchange_strong(futex, &zero, tid)) { + /* + * We took the lock, insert it in the robust list + */ + struct robust_list *list = &head->list; + + /* Error injection to test list_op_pending */ + if (error_inject) + return 0; + + while (list->next != &head->list) + list = list->next; + + list->next = &lock->list; + lock->list.next = &head->list; + + ret = 0; + } else { + /* + * We didn't take the lock, wait until the owner wakes (or dies) + */ + struct timespec to; + + to.tv_sec = FUTEX_TIMEOUT; + to.tv_nsec = 0; + + tid = atomic_load(futex); + /* Kernel ignores futexes without the waiters flag */ + tid |= FUTEX_WAITERS; + atomic_store(futex, tid); + + ret = futex_wait((futex_t *) futex, tid, &to, 0); + + /* + * A real mutex_lock() implementation would loop here to finally + * take the lock. We don't care about that, so we stop here. + */ + } + + head->list_op_pending = NULL; + + return ret; +} + +/* + * This child thread will succeed taking the lock, and then will exit holding it + */ +static int child_fn_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, false); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + /* + * There's a race here: the parent thread needs to be inside + * futex_wait() before the child thread dies, otherwise it will miss the + * wakeup from handle_futex_death() that this child will emit. We wait a + * little bit just to make sure that this happens. + */ + sleep(1); + + return 0; +} + +/* + * Spawns a child thread that will set a robust list, take the lock, register it + * in the robust list and die. The parent thread will wait on this futex, and + * should be waken up when the child exits. + */ +static void test_robustness(void) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + _Atomic(unsigned int) *futex = &lock.futex; + int ret; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + /* + * Lets use a barrier to ensure that the child thread takes the lock + * before the parent + */ + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + /* + * futex_wait() should return 0 and the futex word should be marked with + * FUTEX_OWNER_DIED + */ + ASSERT_EQ(ret, 0); + if (ret != 0) + printf("futex wait returned %d", errno); + + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + wait(NULL); + pthread_barrier_destroy(&barrier); + + ksft_test_result_pass("%s\n", __func__); +} + +/* + * The only valid value for len is sizeof(*head) + */ +static void test_set_robust_list_invalid_size(void) +{ + struct robust_list_head head; + size_t head_size = sizeof(struct robust_list_head); + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = set_robust_list(&head, head_size * 2); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, head_size - 1); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ksft_test_result_pass("%s\n", __func__); +} + +/* + * Test get_robust_list with pid = 0, getting the list of the running thread + */ +static void test_get_robust_list_self(void) +{ + struct robust_list_head head, head2, *get_head; + size_t head_size = sizeof(struct robust_list_head), len_ptr; + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head); + ASSERT_EQ(head_size, len_ptr); + + ret = set_robust_list(&head2, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head2); + ASSERT_EQ(head_size, len_ptr); + + ksft_test_result_pass("%s\n", __func__); +} + +static int child_list(void *arg) +{ + struct robust_list_head *head = (struct robust_list_head *) arg; + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + return 0; +} + +/* + * Test get_robust_list from another thread. We use two barriers here to ensure + * that: + * 1) the child thread set the list before we try to get it from the + * parent + * 2) the child thread still alive when we try to get the list from it + */ +static void test_get_robust_list_child(void) +{ + pid_t tid; + int ret; + struct robust_list_head head, *get_head; + size_t len_ptr; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ret = pthread_barrier_init(&barrier2, NULL, 2); + ASSERT_EQ(ret, 0); + + tid = create_child(&child_list, &head); + ASSERT_NE(tid, -1); + + pthread_barrier_wait(&barrier); + + ret = get_robust_list(tid, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(&head, get_head); + + pthread_barrier_wait(&barrier2); + + wait(NULL); + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); + + ksft_test_result_pass("%s\n", __func__); +} + +static int child_fn_lock_with_error(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, true); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + sleep(1); + + return 0; +} + +/* + * Same as robustness test, but inject an error where the mutex_lock() exits + * earlier, just after setting list_op_pending and taking the lock, to test the + * list_op_pending mechanism + */ +static void test_set_list_op_pending(void) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + _Atomic(unsigned int) *futex = &lock.futex; + int ret; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock_with_error, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + ASSERT_EQ(ret, 0); + if (ret != 0) + printf("futex wait returned %d", errno); + + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + wait(NULL); + pthread_barrier_destroy(&barrier); + + ksft_test_result_pass("%s\n", __func__); +} + +#define CHILD_NR 10 + +static int child_lock_holder(void *arg) +{ + struct lock_struct *locks = (struct lock_struct *) arg; + struct robust_list_head head; + int i; + + set_list(&head); + + for (i = 0; i < CHILD_NR; i++) { + locks[i].futex = 0; + mutex_lock(&locks[i], &head, false); + } + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + sleep(1); + return 0; +} + +static int child_wait_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + pthread_barrier_wait(&barrier2); + ret = mutex_lock(lock, &head, false); + + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + if (!(lock->futex | FUTEX_OWNER_DIED)) + ksft_test_result_fail("futex not marked with FUTEX_OWNER_DIED\n"); + + return 0; +} + +/* + * Test a robust list of more than one element. All the waiters should wake when + * the holder dies + */ +static void test_robust_list_multiple_elements(void) +{ + struct lock_struct locks[CHILD_NR]; + int i, ret; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + ret = pthread_barrier_init(&barrier2, NULL, CHILD_NR + 1); + ASSERT_EQ(ret, 0); + + create_child(&child_lock_holder, &locks); + + /* Wait until the locker thread takes the look */ + pthread_barrier_wait(&barrier); + + for (i = 0; i < CHILD_NR; i++) + create_child(&child_wait_lock, &locks[i]); + + /* Wait for all children to return */ + while (wait(NULL) > 0); + + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); + + ksft_test_result_pass("%s\n", __func__); +} + +static int child_circular_list(void *arg) +{ + static struct robust_list_head head; + struct lock_struct a, b, c; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_list error\n"); + + head.list.next = &a.list; + + /* + * The last element should point to head list, but we short circuit it + */ + a.list.next = &b.list; + b.list.next = &c.list; + c.list.next = &a.list; + + return 0; +} + +/* + * Create a circular robust list. The kernel should be able to destroy the list + * while processing it so it won't be trapped in an infinite loop while handling + * a process exit + */ +static void test_circular_list(void) +{ + create_child(child_circular_list, NULL); + + wait(NULL); + + ksft_test_result_pass("%s\n", __func__); +} + +void usage(char *prog) +{ + printf("Usage: %s\n", prog); + printf(" -c Use color\n"); + printf(" -h Display this help message\n"); + printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", + VQUIET, VCRITICAL, VINFO); +} + +int main(int argc, char *argv[]) +{ + int c; + + while ((c = getopt(argc, argv, "cht:v:")) != -1) { + switch (c) { + case 'c': + log_color(1); + break; + case 'h': + usage(basename(argv[0])); + exit(0); + case 'v': + log_verbosity(atoi(optarg)); + break; + default: + usage(basename(argv[0])); + exit(1); + } + } + + ksft_print_header(); + ksft_set_plan(7); + + test_robustness(); + + test_set_robust_list_invalid_size(); + test_get_robust_list_self(); + test_get_robust_list_child(); + test_set_list_op_pending(); + test_robust_list_multiple_elements(); + test_circular_list(); + + ksft_print_cnts(); + return 0; +}

There are two functions for handling robust lists during the task exit: exit_robust_list() and compat_exit_robust_list(). The first one handles either 64bit or 32bit lists, depending if it's a 64bit or 32bit kernel. The compat_exit_robust_list() only exists in 64bit kernels that supports 32bit syscalls, and handles 32bit lists.

For the new syscall set_robust_list2(), 64bit kernels need to be able to handle 32bit lists despite having or not support for 32bit syscalls, so make compat_exit_robust_list() exist regardless of compat_ config.

Also, use explicitly sizing, otherwise in a 32bit kernel both exit_robust_list() and compat_exit_robust_list() would be the exactly same function, with none of them dealing with 64bit robust lists.

Signed-off-by: André Almeida andrealmeid@igalia.com --- include/linux/compat.h | 12 +----------- include/linux/futex.h | 10 ++++++++++ include/linux/sched.h | 2 +- kernel/futex/core.c | 48 ++++++++++++++++++++++++++++++++---------------- kernel/futex/syscalls.c | 4 ++-- 5 files changed, 46 insertions(+), 30 deletions(-)

diff --git a/include/linux/compat.h b/include/linux/compat.h index 56cebaff0c910fda853a0e2b3d6d0517e55f8b38..968a9135ff486cf9c8be2a18b80cd4c46e890236 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -385,16 +385,6 @@ struct compat_ifconf { compat_caddr_t ifcbuf; };

-struct compat_robust_list { - compat_uptr_t next; -}; - -struct compat_robust_list_head { - struct compat_robust_list list; - compat_long_t futex_offset; - compat_uptr_t list_op_pending; -}; - #ifdef CONFIG_COMPAT_OLD_SIGACTION struct compat_old_sigaction { compat_uptr_t sa_handler; @@ -672,7 +662,7 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t, struct compat_siginfo __user *, int, struct compat_rusage __user *); asmlinkage long -compat_sys_set_robust_list(struct compat_robust_list_head __user *head, +compat_sys_set_robust_list(struct robust_list_head32 __user *head, compat_size_t len); asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, diff --git a/include/linux/futex.h b/include/linux/futex.h index b37193653e6b5d7d562ac08f93d4ee41eb8e72a2..c5b6976909c7d51360e1831e017f4d1544c258fa 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -55,6 +55,16 @@ union futex_key {

#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } }

+struct robust_list32 { + u32 next; +}; + +struct robust_list_head32 { + struct robust_list32 list; + s32 futex_offset; + u32 list_op_pending; +}; + #ifdef CONFIG_FUTEX enum { FUTEX_STATE_OK, diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52c425e46c66427b2f608ba30b3d99..b0f64029d53e8b2ab56f24f77054aa7645a185c5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1333,7 +1333,7 @@ struct task_struct { #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT - struct compat_robust_list_head __user *compat_robust_list; + struct robust_list_head32 __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 90d53fb0ee9e1563c355ef0499df441367e1a46c..f0ac4b897ddbb667fa85daf5853cb47c749d512d 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1144,15 +1144,16 @@ static inline int fetch_robust_entry(struct robust_list __user **entry, return 0; }

+#ifdef CONFIG_64BIT /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ -static void exit_robust_list(struct task_struct *curr) +static void exit_robust_list64(struct task_struct *curr, + struct robust_list_head __user *head) { - struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; @@ -1211,8 +1212,15 @@ static void exit_robust_list(struct task_struct *curr) curr, pip, HANDLE_DEATH_PENDING); } } +#else +static void exit_robust_list64(struct task_struct *curr, + struct robust_list_head __user *head) +{ + pr_warn("32bit kernel should not allow ROBUST_LIST_64BIT"); +} +#endif

-#ifdef CONFIG_COMPAT +#if defined(CONFIG_COMPAT) || !defined(CONFIG_64BIT) static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { @@ -1226,13 +1234,13 @@ static void __user *futex_uaddr(struct robust_list __user *entry, * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int -compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, - compat_uptr_t __user *head, unsigned int *pi) +fetch_robust_entry32(u32 *uentry, struct robust_list __user **entry, + u32 __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT;

- *entry = compat_ptr((*uentry) & ~1); + *entry = (void __user *)(unsigned long)((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1;

return 0; @@ -1244,21 +1252,21 @@ compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **ent * * We silently return on any sign of list-walking problem. */ -static void compat_exit_robust_list(struct task_struct *curr) +static void exit_robust_list32(struct task_struct *curr, + struct robust_list_head32 __user *head) { - struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; - compat_uptr_t uentry, next_uentry, upending; - compat_long_t futex_offset; + u32 uentry, next_uentry, upending; + s32 futex_offset; int rc;

/* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ - if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) + if (fetch_robust_entry32((u32 *)&uentry, &entry, (u32 *)&head->list.next, &pi)) return; /* * Fetch the relative futex offset: @@ -1269,7 +1277,7 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch any possibly pending lock-add first, and handle it * if it exists: */ - if (compat_fetch_robust_entry(&upending, &pending, + if (fetch_robust_entry32(&upending, &pending, &head->list_op_pending, &pip)) return;

@@ -1279,8 +1287,8 @@ static void compat_exit_robust_list(struct task_struct *curr) * Fetch the next entry in the list before calling * handle_futex_death: */ - rc = compat_fetch_robust_entry(&next_uentry, &next_entry, - (compat_uptr_t __user *)&entry->next, &next_pi); + rc = fetch_robust_entry32(&next_uentry, &next_entry, + (u32 __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: @@ -1406,14 +1414,22 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }

static void futex_cleanup(struct task_struct *tsk) { +#ifdef CONFIG_64BIT if (unlikely(tsk->robust_list)) { - exit_robust_list(tsk); + exit_robust_list64(tsk, tsk->robust_list); tsk->robust_list = NULL; } +#else + if (unlikely(tsk->robust_list)) { + exit_robust_list32(tsk, + (struct robust_list_head32 __user *) tsk->robust_list); + tsk->robust_list = NULL; + } +#endif

#ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { - compat_exit_robust_list(tsk); + exit_robust_list32(tsk, tsk->compat_robust_list); tsk->compat_robust_list = NULL; } #endif diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 4b6da9116aa6c33db9796e3055ce0c90b02d7b91..dba193dfd216cc929c8f4d979aa2bcd99237e2d8 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -440,7 +440,7 @@ SYSCALL_DEFINE4(futex_requeue,

#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, + struct robust_list_head32 __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) @@ -455,7 +455,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { - struct compat_robust_list_head __user *head; + struct robust_list_head32 __user *head; unsigned long ret; struct task_struct *p;

Expand the current robust list test for the new set_robust_list2 syscall. Create an option to make it possible to run the same tests using the new syscall, and also add two new relevant test: test long lists (bigger than ROBUST_LIST_LIMIT) and for unaligned addresses.

Signed-off-by: André Almeida andrealmeid@igalia.com --- .../selftests/futex/functional/robust_list.c | 160 ++++++++++++++++++++- 1 file changed, 156 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/futex/functional/robust_list.c b/tools/testing/selftests/futex/functional/robust_list.c index 42690b2440fd29a9b12c46f67f9645ccc93d1147..004ad79ff6171c411fd47e699e3c38889544218e 100644 --- a/tools/testing/selftests/futex/functional/robust_list.c +++ b/tools/testing/selftests/futex/functional/robust_list.c @@ -35,16 +35,45 @@ #include <stddef.h> #include <sys/mman.h> #include <sys/wait.h> +#include <stdint.h>

#define STACK_SIZE (1024 * 1024)

#define FUTEX_TIMEOUT 3

+#define SYS_set_robust_list2 468 + +enum robust_list2_type { + ROBUST_LIST_32BIT, + ROBUST_LIST_64BIT, +}; + static pthread_barrier_t barrier, barrier2;

+bool robust2 = false; + int set_robust_list(struct robust_list_head *head, size_t len) { - return syscall(SYS_set_robust_list, head, len); + int ret, flags; + + if (!robust2) { + return syscall(SYS_set_robust_list, head, len); + } + + if (sizeof(head) == 8) + flags = ROBUST_LIST_64BIT; + else + flags = ROBUST_LIST_32BIT; + + /* + * We act as we have just one list here. We try to use the first slot, + * but if it hasn't been alocated yet we allocate it. + */ + ret = syscall(SYS_set_robust_list2, head, 0, flags); + if (ret == -1 && errno == ENOENT) + ret = syscall(SYS_set_robust_list2, head, -1, flags); + + return ret; }

int get_robust_list(int pid, struct robust_list_head **head, size_t *len_ptr) @@ -246,6 +275,11 @@ static void test_set_robust_list_invalid_size(void) size_t head_size = sizeof(struct robust_list_head); int ret;

+ if (robust2) { + ksft_test_result_skip("This test is only for old robust interface\n"); + return; + } + ret = set_robust_list(&head, head_size); ASSERT_EQ(ret, 0);

@@ -321,6 +355,11 @@ static void test_get_robust_list_child(void) struct robust_list_head head, *get_head; size_t len_ptr;

+ if (robust2) { + ksft_test_result_skip("Not implemented in the new robust interface\n"); + return; + } + ret = pthread_barrier_init(&barrier, NULL, 2); ret = pthread_barrier_init(&barrier2, NULL, 2); ASSERT_EQ(ret, 0); @@ -332,7 +371,7 @@ static void test_get_robust_list_child(void)

ret = get_robust_list(tid, &get_head, &len_ptr); ASSERT_EQ(ret, 0); - ASSERT_EQ(&head, get_head); + ASSERT_EQ(get_head, &head);

pthread_barrier_wait(&barrier2);

@@ -507,11 +546,119 @@ static void test_circular_list(void) ksft_test_result_pass("%s\n", __func__); }

+#define ROBUST_LIST_LIMIT 2048 +#define CHILD_LIST_LIMIT (ROBUST_LIST_LIMIT + 10) + +static int child_robust_list_limit(void *arg) +{ + struct lock_struct *locks; + struct robust_list *list; + struct robust_list_head head; + int ret, i; + + locks = (struct lock_struct *) arg; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_list error\n"); + + /* + * Create a very long list of locks + */ + head.list.next = &locks[0].list; + + list = head.list.next; + for (i = 0; i < CHILD_LIST_LIMIT - 1; i++) { + list->next = &locks[i+1].list; + list = list->next; + } + list->next = &head.list; + + /* + * Grab the lock in the last one, and die without releasing it + */ + mutex_lock(&locks[CHILD_LIST_LIMIT], &head, false); + pthread_barrier_wait(&barrier); + + sleep(1); + + return 0; +} + +/* + * The old robust list used to have a limit of 2048 items from the kernel side. + * After this limit the kernel stops walking the list and ignore the other + * futexes, causing deadlocks. + * + * For the new interface, test if we can wait for a list of more than 2048 + * elements. + */ +static void test_robust_list_limit(void) +{ + struct lock_struct locks[CHILD_LIST_LIMIT + 1]; + _Atomic(unsigned int) *futex = &locks[CHILD_LIST_LIMIT].futex; + struct robust_list_head head; + int ret; + + if (!robust2) { + ksft_test_result_skip("This test is only for new robust interface\n"); + return; + } + + *futex = 0; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + create_child(child_robust_list_limit, locks); + + /* + * After the child thread creates the very long list of locks, wait on + * the last one. + */ + pthread_barrier_wait(&barrier); + ret = mutex_lock(&locks[CHILD_LIST_LIMIT], &head, false); + + if (ret != 0) + printf("futex wait returned %d\n", errno); + ASSERT_EQ(ret, 0); + + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + wait(NULL); + pthread_barrier_destroy(&barrier); + + ksft_test_result_pass("%s\n", __func__); +} + +/* + * The kernel should refuse an unaligned head pointer + */ +static void test_unaligned_address(void) +{ + struct robust_list_head head, *h; + int ret; + + if (!robust2) { + ksft_test_result_skip("This test is only for new robust interface\n"); + return; + } + + h = (struct robust_list_head *) ((uintptr_t) &head + 1); + ret = set_list(h); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); +} + void usage(char *prog) { printf("Usage: %s\n", prog); printf(" -c Use color\n"); printf(" -h Display this help message\n"); + printf(" -n Use robust2 syscall\n"); printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", VQUIET, VCRITICAL, VINFO); } @@ -520,7 +667,7 @@ int main(int argc, char *argv[]) { int c;

- while ((c = getopt(argc, argv, "cht:v:")) != -1) { + while ((c = getopt(argc, argv, "chnt:v:")) != -1) { switch (c) { case 'c': log_color(1); @@ -531,6 +678,9 @@ int main(int argc, char *argv[]) case 'v': log_verbosity(atoi(optarg)); break; + case 'n': + robust2 = true; + break; default: usage(basename(argv[0])); exit(1); @@ -538,7 +688,7 @@ int main(int argc, char *argv[]) }

ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(8);

test_robustness();

@@ -548,6 +698,8 @@ int main(int argc, char *argv[]) test_set_list_op_pending(); test_robust_list_multiple_elements(); test_circular_list(); + test_robust_list_limit(); + test_unaligned_address();

ksft_print_cnts(); return 0;