/* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also system_call.s). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/mm.c': 'copy_page_tables()' */ #include <linux/errno.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/segment.h> #include <linux/ptrace.h> #include <asm/segment.h> #include <asm/system.h> extern "C" void lcall7(void); extern "C" void ret_from_sys_call(void) __asm__("ret_from_sys_call"); #define MAX_TASKS_PER_USER (NR_TASKS/2) extern int shm_fork(struct task_struct *, struct task_struct *); long last_pid=0; static int find_empty_process(void) { int i, task_nr; int this_user_tasks; repeat: if ((++last_pid) & 0xffff8000) last_pid=1; this_user_tasks = 0; for(i=0 ; i < NR_TASKS ; i++) { if (!task[i]) continue; if (task[i]->uid == current->uid) this_user_tasks++; if (task[i]->pid == last_pid || task[i]->pgrp == last_pid) goto repeat; } if (this_user_tasks > MAX_TASKS_PER_USER && current->uid) return -EAGAIN; /* Only the super-user can fill the last available slot */ task_nr = 0; for(i=1 ; i<NR_TASKS ; i++) if (!task[i]) if (task_nr) return task_nr; else task_nr = i; if (task_nr && suser()) return task_nr; return -EAGAIN; } static struct file * copy_fd(struct file * old_file) { struct file * new_file = get_empty_filp(); int error; if (new_file) { memcpy(new_file,old_file,sizeof(struct file)); new_file->f_count = 1; if (new_file->f_inode) new_file->f_inode->i_count++; if (new_file->f_op && new_file->f_op->open) { error = new_file->f_op->open(new_file->f_inode,new_file); if (error) { iput(new_file->f_inode); new_file->f_count = 0; new_file = NULL; } } } return new_file; } int dup_mmap(struct task_struct * tsk) { struct vm_area_struct * mpnt, **p, *tmp; tsk->mmap = NULL; p = &tsk->mmap; for (mpnt = current->mmap ; mpnt ; mpnt = mpnt->vm_next) { tmp = (struct vm_area_struct *) kmalloc(sizeof(struct vm_area_struct), GFP_KERNEL); if (!tmp) return -ENOMEM; *tmp = *mpnt; tmp->vm_task = tsk; tmp->vm_next = NULL; if (tmp->vm_inode) tmp->vm_inode->i_count++; *p = tmp; p = &tmp->vm_next; } return 0; } #define IS_CLONE (regs.orig_eax == __NR_clone) #define copy_vm(p) ((clone_flags & COPYVM)?copy_page_tables(p):clone_page_tables(p)) /* * Ok, this is the main fork-routine. It copies the system process * information (task[nr]) and sets up the necessary registers. It * also copies the data segment in it's entirety. */ extern "C" int sys_fork(struct pt_regs regs) { struct pt_regs * childregs; struct task_struct *p; int i,nr; struct file *f; unsigned long clone_flags = COPYVM | SIGCHLD; p = (struct task_struct *) __get_free_page(GFP_KERNEL); if (!p) goto bad_fork; nr = find_empty_process(); if (nr < 0) goto bad_fork_free; task[nr] = p; *p = *current; p->kernel_stack_page = 0; p->state = TASK_UNINTERRUPTIBLE; p->flags &= ~(PF_PTRACED|PF_TRACESYS); p->pid = last_pid; p->swappable = 1; p->p_pptr = p->p_opptr = current; p->p_cptr = NULL; SET_LINKS(p); p->signal = 0; p->it_real_value = p->it_virt_value = p->it_prof_value = 0; p->it_real_incr = p->it_virt_incr = p->it_prof_incr = 0; p->leader = 0; /* process leadership doesn't inherit */ p->utime = p->stime = 0; p->cutime = p->cstime = 0; p->min_flt = p->maj_flt = 0; p->cmin_flt = p->cmaj_flt = 0; p->start_time = jiffies; /* * set up new TSS and kernel stack */ p->kernel_stack_page = __get_free_page(GFP_KERNEL); if (!p->kernel_stack_page) goto bad_fork_cleanup; p->tss.es = KERNEL_DS; p->tss.cs = KERNEL_CS; p->tss.ss = KERNEL_DS; p->tss.ds = KERNEL_DS; p->tss.fs = KERNEL_DS; p->tss.gs = KERNEL_DS; p->tss.ss0 = KERNEL_DS; p->tss.esp0 = p->kernel_stack_page + PAGE_SIZE; p->tss.tr = _TSS(nr); childregs = ((struct pt_regs *) (p->kernel_stack_page + PAGE_SIZE)) - 1; p->tss.esp = (unsigned long) childregs; p->tss.eip = (unsigned long) ret_from_sys_call; *childregs = regs; childregs->eax = 0; p->tss.back_link = 0; p->tss.eflags = regs.eflags & 0xffffcfff; /* iopl is always 0 for a new process */ if (IS_CLONE) { if (regs.ebx) childregs->esp = regs.ebx; clone_flags = regs.ecx; if (childregs->esp == regs.esp) clone_flags |= COPYVM; } p->exit_signal = clone_flags & CSIGNAL; p->tss.ldt = _LDT(nr); p->tss.bitmap = offsetof(struct tss_struct,io_bitmap); set_call_gate(p->ldt+0,lcall7); for (i = 0; i < IO_BITMAP_SIZE+1 ; i++) /* IO bitmap is actually SIZE+1 */ p->tss.io_bitmap[i] = ~0; if (last_task_used_math == current) __asm__("clts ; fnsave %0 ; frstor %0":"=m" (p->tss.i387)); p->semun = NULL; p->shm = NULL; if (copy_vm(p) || shm_fork(current, p)) goto bad_fork_cleanup; if (clone_flags & COPYFD) { for (i=0; i<NR_OPEN;i++) if ((f = p->filp[i]) != NULL) p->filp[i] = copy_fd(f); } else { for (i=0; i<NR_OPEN;i++) if ((f = p->filp[i]) != NULL) f->f_count++; } if (current->pwd) current->pwd->i_count++; if (current->root) current->root->i_count++; if (current->executable) current->executable->i_count++; dup_mmap(p); set_tss_desc(gdt+(nr<<1)+FIRST_TSS_ENTRY,&(p->tss)); set_ldt_desc(gdt+(nr<<1)+FIRST_LDT_ENTRY,&(p->ldt)); p->counter = current->counter >> 1; p->state = TASK_RUNNING; /* do this last, just in case */ return p->pid; bad_fork_cleanup: task[nr] = NULL; REMOVE_LINKS(p); free_page(p->kernel_stack_page); bad_fork_free: free_page((long) p); bad_fork: return -EAGAIN; }