nuttx/sched/task/task_exit.c

176 lines
5.3 KiB
C
Raw Normal View History

/****************************************************************************
* sched/task/task_exit.c
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership. The
* ASF licenses this file to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance with the
* License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
****************************************************************************/
/****************************************************************************
* Included Files
****************************************************************************/
#include <nuttx/config.h>
#include <sched.h>
#include <nuttx/debug.h>
#include <nuttx/sched_note.h>
#include "sched/sched.h"
#ifdef CONFIG_SMP
# include "irq/irq.h"
#endif
Squashed commit of the following: libs/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. syscall/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. wireless/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. Documentation/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. include/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. drivers/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. sched/: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. configs: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. arch/xtensa: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. arch/z80: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. arch/x86: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. arch/renesas and arch/risc-v: Remove references to CONFIG_DISABLE_SIGNALS. Signals can no longer be disabled. arch/or1k: Remove all references to CONFIG_DISABLE_SIGNALS. Signals are always enabled. arch/misoc: Remove all references to CONFIG_DISABLE_SIGNALS. Signals are always enabled. arch/mips: Remove all references to CONFIG_DISABLE_SIGNALS. Signals are always enabled. arch/avr: Remove all references to CONFIG_DISABLE_SIGNALS. Signals are always enabled. arch/arm: Remove all references to CONFIG_DISABLE_SIGNALS. Signals are always enabled.
2019-04-29 14:52:05 -06:00
#include "signal/signal.h"
#include "task/task.h"
/****************************************************************************
* Public Functions
****************************************************************************/
/****************************************************************************
* Name: nxtask_exit
*
* Description:
* This is a part of the logic used to implement _exit(). The full
* implementation of _exit() is architecture-dependent. The _exit()
* function also implements the bottom half of exit() and pthread_exit().
*
* This function causes the currently running task (i.e., the task at the
* head of the ready-to-run list) to cease to exist. This function should
* never be called from normal user code, but only from the architecture-
* specific implementation of exit.
*
2020-03-08 05:51:34 -07:00
* Threads/tasks could also be terminated via pthread_cancel,
* task_delete(), and task_restart(). In the last two cases, the
* task will be terminated as though exit() were called.
*
* Input Parameters:
* None
*
* Returned Value:
* OK on success; or ERROR on failure
*
* Assumptions:
* Executing within a critical section established by the caller.
*
****************************************************************************/
int nxtask_exit(void)
{
FAR struct tcb_s *dtcb;
FAR struct tcb_s *rtcb;
int ret;
#ifdef CONFIG_SMP
/* Avoid using this_task() because it may assume a state that is not
* appropriate for an exiting task.
*/
dtcb = current_task(this_cpu());
#else
dtcb = this_task();
#endif
sinfo("%s pid=%d,TCB=%p\n", get_task_name(dtcb),
dtcb->pid, dtcb);
2020-03-08 05:51:34 -07:00
/* Remove the TCB of the current task from the ready-to-run list. A
* context switch will definitely be necessary -- that must be done
* by the architecture-specific logic.
*
* nxsched_remove_readytorun will mark the task at the head of the
2020-03-08 05:51:34 -07:00
* ready-to-run with state == TSTATE_TASK_RUNNING
*/
nxsched_remove_self(dtcb);
/* Get the new task at the head of the ready to run list */
#ifdef CONFIG_SMP
rtcb = current_task(this_cpu());
#else
rtcb = this_task();
#endif
/* We are now in a bad state -- the head of the ready to run task list
* does not correspond to the thread that is running. Disabling pre-
* emption on this TCB and marking the new ready-to-run task as not
* running.
*
* We disable pre-emption here by directly incrementing the lockcount
* (vs. calling sched_lock()).
*/
rtcb->lockcount++;
rtcb->task_state = TSTATE_TASK_READYTORUN;
#ifdef CONFIG_SMP
/* NOTE:
* During nxtask_terminate(), enter_critical_section() will be called
2021-02-25 09:48:46 -03:00
* to deallocate tcb. However, this would acquire g_cpu_irqlock if
* rtcb->irqcount = 0, event though we are in critical section.
2021-02-25 09:48:46 -03:00
* To prevent from acquiring, increment rtcb->irqcount here.
*/
rtcb->irqcount++;
#endif
dtcb->task_state = TSTATE_TASK_INACTIVE;
/* Update scheduler parameters.
*
* When the thread exits, SYS_restore_context is called to
* restore the context, which does not update the scheduling
* information.
* We need to update the scheduling information before tcb is released.
*/
nxsched_switch_context(dtcb, rtcb);
sched_note_stop(dtcb);
ret = nxsched_release_tcb(dtcb, dtcb->flags & TCB_FLAG_TTYPE_MASK);
#ifdef CONFIG_SMP
rtcb->irqcount--;
#endif
rtcb->task_state = TSTATE_TASK_RUNNING;
/* Decrement the lockcount on rctb. */
rtcb->lockcount--;
!sched/arch/libc: Give fork() and vfork() their real, separate semantics. NuttX implemented fork() and vfork() as the same function. Both were libc wrappers around a single up_fork() syscall; vfork() differed only by a trailing waitpid(). Underneath, the child joined the parent's address environment -- the same addrenv_join() that pthread_create() uses -- and got a private copy of the stack. So the child shared .data, .bss and the heap with its parent and ran concurrently with it. That is not fork(). It is vfork()-with-a-private-stack under fork()'s name, and the history says so: today's fork() is NuttX's old vfork(), renamed in c33d1c9c97 (2023) without any change of behaviour. The failure was silent -- a program written against POSIX fork() compiled, ran, and had its child's writes land in the parent's variables. Separate them into two primitives, chosen by which function the caller called rather than by what the hardware happens to be: fork() child gets its own copy of the parent's memory at the same virtual addresses; runs concurrently. Only where an address environment can be duplicated -- elsewhere it is not declared at all, so calling it is a build error naming the function. vfork() child shares the parent's memory; parent suspended until the child _exit()s or exec()s. Implementable everywhere. Below libc there is still one syscall. up_fork() gains a bool saying which primitive the caller used, since the per-architecture register snapshot is the same for both, and passes it to nxtask_setup_fork(), which is the single place the memory semantics are decided. The argument arrives in the first argument register and is never touched: each architecture's snapshot takes some other call-clobbered register for its scratch, so the flag is simply still there when the C worker is called. The vfork() parent suspension moves out of libc into nxtask_start_fork(), released from nxsched_release_tcb() by nxtask_resume_vfork(). Two things follow: the parent is resumed at exec(), since exec_swap() has already handed the child's pid to the loaded program by the time the vfork stub exits, and vfork() no longer depends on CONFIG_SCHED_WAITPID. Releasing there requires one fix in nxtask_exit(). It raises rtcb->lockcount directly rather than through sched_lock() while it tears the TCB down, so the nxsem_post() that wakes the vfork() parent leaves it queued where a blocked task collects while pre-emption is off -- g_pendingtasks, or g_readytorun on SMP -- and the matching raw lockcount-- does not publish it the way sched_unlock() would, leaving the parent stranded with nothing to move it on. The fix mirrors sched_unlock() for each case: nxsched_merge_pending(), or nxsched_deliver_task() under CONFIG_SMP. Both are no-ops while pre-emption is still disabled, and up_exit() re-reads this_task() afterwards, so a change of the ready-to-run head is honoured. Without it vfork() deadlocks wherever no other task happens to call sched_unlock() afterwards -- rv-virt:nsh64 and rv-virt:pnsh64, where NSH is blocked in waitpid() holding the lock, and qemu-armv8a:citest_smp, which hangs the moment the vfork() test runs. fork() is built on a new addrenv_fork(), backed by an up_addrenv_fork() hook that duplicates an address environment into freshly allocated pages mapped at the same virtual addresses -- unlike up_addrenv_clone(), which copies only the representation and leaves both pointing at the same page tables. The child then adopts the parent's stack geometry rather than being given a relocated copy: a pointer to a stack local taken before fork() must name the same object in the child that it named in the parent, and the parent's stack is already in the duplicate, with its contents, at the parent's address. No architecture implements up_addrenv_fork() yet, so this commit leaves fork() unavailable everywhere. That is the intended state. It withdraws fork() from ARCH_ARM, flat ARCH_ARM64, ARCH_RISCV, ARCH_SIM and ARCH_X86_64, where until now it named the sharing primitive; per-architecture patches restore it, with POSIX semantics, as up_addrenv_fork() lands. In the meantime the sharing primitive is still there under the name that describes it: vfork() for a child that runs a program, pthread_create() for a second flow of control that shares memory, posix_spawn() for both at once. Kconfig: ARCH_HAVE_VFORK inherits ARCH_HAVE_FORK's select lines, conditions included, so no configuration gains machinery; ARCH_HAVE_FORK is redefined to mean "can provide POSIX fork() semantics" and now depends on ARCH_ADDRENV. There is one deliberate departure from "verbatim". ARCH_ARM selected the fork family unconditionally, BUILD_KERNEL included, and that has never worked: on a kernel build the architecture's fork entry point sees the kernel's return address and stack pointer rather than the caller's, so the child resumes at a kernel address. On qemu-armv7a:knsh master faults in ostest's fork case with "Child did not run" and then a data abort; without the condition this change faults the same way through vfork(). ARCH_ARM64 and ARCH_X86_64 already carried "if !BUILD_KERNEL" for exactly this reason -- ARM was the outlier. Conditioning it turns a runtime fault into an honest absence, which is the whole point of the change; arch/arm takes the condition off again in the patch that adds its saved-syscall-frame path. Only the MMU-capable ARM ports are affected, since Cortex-M cannot build BUILD_KERNEL at all. Also fixes two latent syntax errors found on the way: a missing comma in riscv_fork.c and mips_fork.c, both in *_FRAMEPOINTER && !SAVE_GP branches that are never compiled today. BREAKING CHANGE: fork() is withdrawn from every architecture. It is no longer declared in unistd.h, so code that calls it fails to build with an error naming the function, and the sharing behaviour it used to have is gone rather than renamed. CONFIG_ARCH_HAVE_FORK no longer means "fork() exists"; it means "this configuration can provide POSIX fork() semantics", and no architecture selects it yet. Quick fix, chosen by why the call was made: to run a program vfork() + exec*(), or better posix_spawn() a second flow of control that pthread_create() shares the caller's memory a genuinely independent copy keep fork(), and wait for the per-arch patch of the process that implements up_addrenv_fork() and selects CONFIG_ARCH_HAVE_FORK Out-of-tree code that tests CONFIG_ARCH_HAVE_FORK to decide whether a fork-then-exec path is available wants CONFIG_ARCH_HAVE_VFORK instead, which is selected in exactly the places CONFIG_ARCH_HAVE_FORK used to be. The full migration guide is Documentation/guides/fork_vfork_migration.rst. Assisted-by: Claude Code:claude-opus-5 Signed-off-by: Marco Casaroli <marco.casaroli@gmail.com>
2026-08-07 12:12:59 +02:00
/* Publish anything woken while the TCB was being released. lockcount was
* raised directly rather than through sched_lock(), so the matching
* decrement above does not publish the way sched_unlock() would, and a
* vfork() parent released by nxsched_release_tcb() would be stranded --
* in g_pendingtasks, or in g_readytorun on SMP. This mirrors what
* sched_unlock() does for each case.
*/
#ifdef CONFIG_SMP
nxsched_deliver_task(this_cpu(), rtcb->cpu, SWITCH_HIGHER);
#else
nxsched_merge_pending();
#endif
return ret;
}