glibc/sysdeps/nptl/lowlevellock-futex.h

131 lines
5.2 KiB
C
Raw Normal View History

/* Low-level locking access to futex facilities. Stub version.
Copyright (C) 2014-2025 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library. If not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
<https://www.gnu.org/licenses/>. */
#ifndef _LOWLEVELLOCK_FUTEX_H
#define _LOWLEVELLOCK_FUTEX_H 1
#ifndef __ASSEMBLER__
# include <sysdep.h>
# include <kernel-features.h>
#endif
#define FUTEX_WAIT 0
#define FUTEX_WAKE 1
#define FUTEX_REQUEUE 3
#define FUTEX_CMP_REQUEUE 4
#define FUTEX_WAKE_OP 5
#define FUTEX_OP_CLEAR_WAKE_IF_GT_ONE ((4 << 24) | 1)
#define FUTEX_LOCK_PI 6
#define FUTEX_UNLOCK_PI 7
#define FUTEX_TRYLOCK_PI 8
#define FUTEX_WAIT_BITSET 9
#define FUTEX_WAKE_BITSET 10
#define FUTEX_WAIT_REQUEUE_PI 11
#define FUTEX_CMP_REQUEUE_PI 12
#define FUTEX_LOCK_PI2 13
#define FUTEX_PRIVATE_FLAG 128
#define FUTEX_CLOCK_REALTIME 256
#define FUTEX_BITSET_MATCH_ANY 0xffffffff
/* Values for 'private' parameter of locking macros. Yes, the
definition seems to be backwards. But it is not. The bit will be
reversed before passing to the system call. */
#define LLL_PRIVATE 0
#define LLL_SHARED FUTEX_PRIVATE_FLAG
#ifndef __ASSEMBLER__
# define __lll_private_flag(fl, private) \
(((fl) | FUTEX_PRIVATE_FLAG) ^ (private))
# define lll_futex_syscall(nargs, futexp, op, ...) \
({ \
long int __ret = INTERNAL_SYSCALL (futex, nargs, futexp, op, \
__VA_ARGS__); \
(__glibc_unlikely (INTERNAL_SYSCALL_ERROR_P (__ret)) \
? -INTERNAL_SYSCALL_ERRNO (__ret) : 0); \
})
/* For most of these macros, the return value is never really used.
Nevertheless, the protocol is that each one returns a negated errno
code for failure or zero for success. (Note that the corresponding
Linux system calls can sometimes return positive values for success
cases too. We never use those values.) */
/* Wait while *FUTEXP == VAL for an lll_futex_wake call on FUTEXP. */
# define lll_futex_wait(futexp, val, private) \
lll_futex_timed_wait (futexp, val, NULL, private)
# define lll_futex_timed_wait(futexp, val, timeout, private) \
lll_futex_syscall (4, futexp, \
__lll_private_flag (FUTEX_WAIT, private), \
val, timeout)
nptl: Add clockid parameter to futex timed wait calls In preparation for adding POSIX clockwait variants of timedwait functions, add a clockid_t parameter to futex_abstimed_wait functions and pass CLOCK_REALTIME from all callers for the time being. Replace lll_futex_timed_wait_bitset with lll_futex_clock_wait_bitset which takes a clockid_t parameter rather than the magic clockbit. * sysdeps/nptl/lowlevellock-futex.h, sysdeps/unix/sysv/linux/lowlevellock-futex.h: Replace lll_futex_timed_wait_bitset with lll_futex_clock_wait_bitset that takes a clockid rather than a special clockbit. * sysdeps/nptl/lowlevellock-futex.h: Add lll_futex_supported_clockid so that client functions can check whether their clockid parameter is valid even if they don't ultimately end up calling lll_futex_clock_wait_bitset. * sysdeps/nptl/futex-internal.h, sysdeps/unix/sysv/linux/futex-internal.h (futex_abstimed_wait, futex_abstimed_wait_cancelable): Add clockid_t parameter to indicate which clock the absolute time passed should be measured against. Pass that clockid onto lll_futex_clock_wait_bitset. Add invalid clock as reason for returning -EINVAL. * sysdeps/nptl/futex-internal.h, sysdeps/unix/sysv/linux/futex-internal.h: Introduce futex_abstimed_supported_clockid so that client functions can check whether their clockid parameter is valid even if they don't ultimately end up calling futex_abstimed_wait. * nptl/pthread_cond_wait.c (__pthread_cond_wait_common): Remove code to calculate relative timeout for __PTHREAD_COND_CLOCK_MONOTONIC_MASK and just pass CLOCK_MONOTONIC or CLOCK_REALTIME as required to futex_abstimed_wait_cancelable. * nptl/pthread_rwlock_common (__pthread_rwlock_rdlock_full) (__pthread_wrlock_full), nptl/sem_waitcommon (do_futex_wait): Pass additional CLOCK_REALTIME to futex_abstimed_wait_cancelable. * nptl/pthread_mutex_timedlock.c (__pthread_mutex_timedlock): Switch to lll_futex_clock_wait_bitset and pass CLOCK_REALTIME Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
2019-06-21 14:53:40 +00:00
/* Verify whether the supplied clockid is supported by
lll_futex_clock_wait_bitset. */
# define lll_futex_supported_clockid(clockid) \
((clockid) == CLOCK_REALTIME || (clockid) == CLOCK_MONOTONIC)
/* Wake up up to NR waiters on FUTEXP. */
# define lll_futex_wake(futexp, nr, private) \
lll_futex_syscall (4, futexp, \
__lll_private_flag (FUTEX_WAKE, private), nr, 0)
/* Wake up up to NR_WAKE waiters on FUTEXP. Move up to NR_MOVE of the
rest from waiting on FUTEXP to waiting on MUTEX (a different futex).
Returns non-zero if error happened, zero if success. */
# define lll_futex_requeue(futexp, nr_wake, nr_move, mutex, val, private) \
lll_futex_syscall (6, futexp, \
__lll_private_flag (FUTEX_CMP_REQUEUE, private), \
nr_wake, nr_move, mutex, val)
/* Wake up up to NR_WAKE waiters on FUTEXP and NR_WAKE2 on FUTEXP2.
Returns non-zero if error happened, zero if success. */
# define lll_futex_wake_unlock(futexp, nr_wake, nr_wake2, futexp2, private) \
lll_futex_syscall (6, futexp, \
__lll_private_flag (FUTEX_WAKE_OP, private), \
nr_wake, nr_wake2, futexp2, \
FUTEX_OP_CLEAR_WAKE_IF_GT_ONE)
#define lll_futex_timed_unlock_pi(futexp, private) \
lll_futex_syscall (4, futexp, \
__lll_private_flag (FUTEX_UNLOCK_PI, private), \
0, 0)
/* Like lll_futex_requeue, but pairs with lll_futex_wait_requeue_pi
and inherits priority from the waiter. */
# define lll_futex_cmp_requeue_pi(futexp, nr_wake, nr_move, mutex, \
val, private) \
lll_futex_syscall (6, futexp, \
__lll_private_flag (FUTEX_CMP_REQUEUE_PI, \
private), \
nr_wake, nr_move, mutex, val)
nptl: Reinstate pthread_timedjoin_np as a cancellation point (BZ#24215) Patch ce7eb0e90315 ("nptl: Cleanup cancellation macros") changed the join sequence for internal common __pthread_timedjoin_ex to use the new macro lll_wait_tid. The idea was this macro would issue the cancellable futex operation depending whether the timeout is used or not. However if a timeout is used, __lll_timedwait_tid is called and it is not a cancellable entrypoint. This patch fixes it by simplifying the code in various ways: - Instead of adding the cancellation handling on __lll_timedwait_tid, it moves the generic implementation to pthread_join_common.c (called now timedwait_tid with some fixes to use the correct type for pid). - The llvm_wait_tid macro is removed, along with its replication on x86_64, i686, and sparc arch-specific lowlevellock.h. - sparc32 __lll_timedwait_tid is also removed, since the code is similar to generic one. - x86_64 and i386 provides arch-specific __lll_timedwait_tid which is also removed since they are similar in functionality to generic C code and there is no indication it is better than compiler generated code. New tests, tst-join8 and tst-join9, are provided to check if pthread_timedjoin_np acts as a cancellation point. Checked on x86_64-linux-gnu, i686-linux-gnu, sparcv9-linux-gnu, and aarch64-linux-gnu. [BZ #24215] * nptl/Makefile (lpthread-routines): Remove lll_timedwait_tid. (tests): Add tst-join8 tst-join9. * nptl/lll_timedwait_tid.c: Remove file. * sysdeps/sparc/sparc32/lll_timedwait_tid.c: Likewise. * sysdeps/unix/sysv/linux/i386/lll_timedwait_tid.c: Likewise. * sysdeps/sysv/linux/x86_64/lll_timedwait_tid.c: Likewise. * nptl/pthread_join_common.c (timedwait_tid): New function. (__pthread_timedjoin_ex): Act as cancellation entrypoint is block is set. * nptl/tst-join5.c (thread_join): New function. (tf1, tf2, do_test): Use libsupport and add pthread_timedjoin_np check. * nptl/tst-join8.c: New file. * nptl/tst-join9.c: Likewise. * sysdeps/nptl/lowlevellock-futex.h (lll_futex_wait_cancel, lll_futex_timed_wait_cancel): Add generic macros. * sysdeps/nptl/lowlevellock.h (__lll_timedwait_tid, lll_wait_tid): Remove definitions. * sysdeps/unix/sysv/linux/i386/lowlevellock.h: Likewise. * sysdeps/unix/sysv/linux/sparc/lowlevellock.h: Likewise. * sysdeps/unix/sysv/linux/x86_64/lowlevellock.h: Likewise. * sysdeps/sparc/sparc32/lowlevellock.c (__lll_timedwait_tid): Remove function. * sysdeps/unix/sysv/linux/i386/lowlevellock.S (__lll_timedwait_tid): Likewise. * sysdeps/unix/sysv/linux/x86_64/lowlevellock.S: Likewise. * sysdeps/unix/sysv/linux/lowlevellock-futex.h (lll_futex_timed_wait_cancel): New macro.
2019-02-12 14:36:46 +00:00
/* Like lll_futex_wait, but acting as a cancellable entrypoint. */
nptl: Fix Race conditions in pthread cancellation [BZ#12683] The current racy approach is to enable asynchronous cancellation before making the syscall and restore the previous cancellation type once the syscall returns, and check if cancellation has happen during the cancellation entrypoint. As described in BZ#12683, this approach shows 2 problems: 1. Cancellation can act after the syscall has returned from the kernel, but before userspace saves the return value. It might result in a resource leak if the syscall allocated a resource or a side effect (partial read/write), and there is no way to program handle it with cancellation handlers. 2. If a signal is handled while the thread is blocked at a cancellable syscall, the entire signal handler runs with asynchronous cancellation enabled. This can lead to issues if the signal handler call functions which are async-signal-safe but not async-cancel-safe. For the cancellation to work correctly, there are 5 points at which the cancellation signal could arrive: [ ... )[ ... )[ syscall ]( ... 1 2 3 4 5 1. Before initial testcancel, e.g. [*... testcancel) 2. Between testcancel and syscall start, e.g. [testcancel...syscall start) 3. While syscall is blocked and no side effects have yet taken place, e.g. [ syscall ] 4. Same as 3 but with side-effects having occurred (e.g. a partial read or write). 5. After syscall end e.g. (syscall end...*] And libc wants to act on cancellation in cases 1, 2, and 3 but not in cases 4 or 5. For the 4 and 5 cases, the cancellation will eventually happen in the next cancellable entrypoint without any further external event. The proposed solution for each case is: 1. Do a conditional branch based on whether the thread has received a cancellation request; 2. It can be caught by the signal handler determining that the saved program counter (from the ucontext_t) is in some address range beginning just before the "testcancel" and ending with the syscall instruction. 3. SIGCANCEL can be caught by the signal handler and determine that the saved program counter (from the ucontext_t) is in the address range beginning just before "testcancel" and ending with the first uninterruptable (via a signal) syscall instruction that enters the kernel. 4. In this case, except for certain syscalls that ALWAYS fail with EINTR even for non-interrupting signals, the kernel will reset the program counter to point at the syscall instruction during signal handling, so that the syscall is restarted when the signal handler returns. So, from the signal handler's standpoint, this looks the same as case 2, and thus it's taken care of. 5. For syscalls with side-effects, the kernel cannot restart the syscall; when it's interrupted by a signal, the kernel must cause the syscall to return with whatever partial result is obtained (e.g. partial read or write). 6. The saved program counter points just after the syscall instruction, so the signal handler won't act on cancellation. This is similar to 4. since the program counter is past the syscall instruction. So The proposed fixes are: 1. Remove the enable_asynccancel/disable_asynccancel function usage in cancellable syscall definition and instead make them call a common symbol that will check if cancellation is enabled (__syscall_cancel at nptl/cancellation.c), call the arch-specific cancellable entry-point (__syscall_cancel_arch), and cancel the thread when required. 2. Provide an arch-specific generic system call wrapper function that contains global markers. These markers will be used in SIGCANCEL signal handler to check if the interruption has been called in a valid syscall and if the syscalls has side-effects. A reference implementation sysdeps/unix/sysv/linux/syscall_cancel.c is provided. However, the markers may not be set on correct expected places depending on how INTERNAL_SYSCALL_NCS is implemented by the architecture. It is expected that all architectures add an arch-specific implementation. 3. Rewrite SIGCANCEL asynchronous handler to check for both canceling type and if current IP from signal handler falls between the global markers and act accordingly. 4. Adjust libc code to replace LIBC_CANCEL_ASYNC/LIBC_CANCEL_RESET to use the appropriate cancelable syscalls. 5. Adjust 'lowlevellock-futex.h' arch-specific implementations to provide cancelable futex calls. Some architectures require specific support on syscall handling: * On i386 the syscall cancel bridge needs to use the old int80 instruction because the optimized vDSO symbol the resulting PC value for an interrupted syscall points to an address outside the expected markers in __syscall_cancel_arch. It has been discussed in LKML [1] on how kernel could help userland to accomplish it, but afaik discussion has stalled. Also, sysenter should not be used directly by libc since its calling convention is set by the kernel depending of the underlying x86 chip (check kernel commit 30bfa7b3488bfb1bb75c9f50a5fcac1832970c60). * mips o32 is the only kABI that requires 7 argument syscall, and to avoid add a requirement on all architectures to support it, mips support is added with extra internal defines. Checked on aarch64-linux-gnu, arm-linux-gnueabihf, powerpc-linux-gnu, powerpc64-linux-gnu, powerpc64le-linux-gnu, i686-linux-gnu, and x86_64-linux-gnu. [1] https://lkml.org/lkml/2016/3/8/1105 Reviewed-by: Carlos O'Donell <carlos@redhat.com>
2024-06-25 19:17:44 +00:00
# define lll_futex_wait_cancel(futexp, val, private) \
({ \
int __op = __lll_private_flag (FUTEX_WAIT, private); \
INTERNAL_SYSCALL_CANCEL (futex, futexp, __op, val, NULL); \
})
#endif /* !__ASSEMBLER__ */
#endif /* lowlevellock-futex.h */