Operating System (5) : 用户进程管理

/* load_icode - load the content of binary program(ELF format) as the new content of current process
 * @binary:  the memory addr of the content of binary program
 * @size:  the size of the content of binary program
 */
static int
load_icode(unsigned char *binary, size_t size) {
    if (current->mm != NULL) {
        panic("load_icode: current->mm must be empty.\n");
    }

    int ret = -E_NO_MEM;
    struct mm_struct *mm;
    //(1) create a new mm for current process
    if ((mm = mm_create()) == NULL) {
        goto bad_mm;
    }
    //(2) create a new PDT, and mm->pgdir= kernel virtual addr of PDT
    if (setup_pgdir(mm) != 0) {
        goto bad_pgdir_cleanup_mm;
    }
    //(3) copy TEXT/DATA section, build BSS parts in binary to memory space of process
    struct Page *page;
    //(3.1) get the file header of the bianry program (ELF format)
    struct elfhdr *elf = (struct elfhdr *)binary;
    //(3.2) get the entry of the program section headers of the bianry program (ELF format)
    struct proghdr *ph = (struct proghdr *)(binary + elf->e_phoff);
    //(3.3) This program is valid?
    if (elf->e_magic != ELF_MAGIC) {
        ret = -E_INVAL_ELF;
        goto bad_elf_cleanup_pgdir;
    }

    uint32_t vm_flags, perm;
    struct proghdr *ph_end = ph + elf->e_phnum;
    for (; ph < ph_end; ph ++) {
    //(3.4) find every program section headers
        if (ph->p_type != ELF_PT_LOAD) {
            continue ;
        }
        if (ph->p_filesz > ph->p_memsz) {
            ret = -E_INVAL_ELF;
            goto bad_cleanup_mmap;
        }
        if (ph->p_filesz == 0) {
            continue ;
        }
    //(3.5) call mm_map fun to setup the new vma ( ph->p_va, ph->p_memsz)
        vm_flags = 0, perm = PTE_U;
        if (ph->p_flags & ELF_PF_X) vm_flags |= VM_EXEC;
        if (ph->p_flags & ELF_PF_W) vm_flags |= VM_WRITE;
        if (ph->p_flags & ELF_PF_R) vm_flags |= VM_READ;
        if (vm_flags & VM_WRITE) perm |= PTE_W;
        if ((ret = mm_map(mm, ph->p_va, ph->p_memsz, vm_flags, NULL)) != 0) {
            goto bad_cleanup_mmap;
        }
        unsigned char *from = binary + ph->p_offset;
        size_t off, size;
        uintptr_t start = ph->p_va, end, la = ROUNDDOWN(start, PGSIZE);

        ret = -E_NO_MEM;

     //(3.6) alloc memory, and  copy the contents of every program section (from, from+end) to process's memory (la, la+end)
        end = ph->p_va + ph->p_filesz;
     //(3.6.1) copy TEXT/DATA section of bianry program
        while (start < end) {
            if ((page = pgdir_alloc_page(mm->pgdir, la, perm)) == NULL) {
                goto bad_cleanup_mmap;
            }
            off = start - la, size = PGSIZE - off, la += PGSIZE;
            if (end < la) {
                size -= la - end;
            }
            memcpy(page2kva(page) + off, from, size);
            start += size, from += size;
        }

      //(3.6.2) build BSS section of binary program
        end = ph->p_va + ph->p_memsz;
        if (start < la) {
            /* ph->p_memsz == ph->p_filesz */
            if (start == end) {
                continue ;
            }
            off = start + PGSIZE - la, size = PGSIZE - off;
            if (end < la) {
                size -= la - end;
            }
            memset(page2kva(page) + off, 0, size);
            start += size;
            assert((end < la && start == end) || (end >= la && start == la));
        }
        while (start < end) {
            if ((page = pgdir_alloc_page(mm->pgdir, la, perm)) == NULL) {
                goto bad_cleanup_mmap;
            }
            off = start - la, size = PGSIZE - off, la += PGSIZE;
            if (end < la) {
                size -= la - end;
            }
            memset(page2kva(page) + off, 0, size);
            start += size;
        }
    }
    //(4) build user stack memory
    vm_flags = VM_READ | VM_WRITE | VM_STACK;
    if ((ret = mm_map(mm, USTACKTOP - USTACKSIZE, USTACKSIZE, vm_flags, NULL)) != 0) {
        goto bad_cleanup_mmap;
    }
    assert(pgdir_alloc_page(mm->pgdir, USTACKTOP-PGSIZE , PTE_USER) != NULL);
    assert(pgdir_alloc_page(mm->pgdir, USTACKTOP-2*PGSIZE , PTE_USER) != NULL);
    assert(pgdir_alloc_page(mm->pgdir, USTACKTOP-3*PGSIZE , PTE_USER) != NULL);
    assert(pgdir_alloc_page(mm->pgdir, USTACKTOP-4*PGSIZE , PTE_USER) != NULL);
    
    //(5) set current process's mm, sr3, and set CR3 reg = physical addr of Page Directory
    mm_count_inc(mm);
    current->mm = mm;
    current->cr3 = PADDR(mm->pgdir);
    lcr3(PADDR(mm->pgdir));

    //(6) setup trapframe for user environment
    struct trapframe *tf = current->tf;
    memset(tf, 0, sizeof(struct trapframe));
    /* LAB5:EXERCISE1 
     * should set tf_cs,tf_ds,tf_es,tf_ss,tf_esp,tf_eip,tf_eflags
     * NOTICE: If we set trapframe correctly, then the user level process can return to USER MODE from kernel. So
     *          tf_cs should be USER_CS segment (see memlayout.h)
     *          tf_ds=tf_es=tf_ss should be USER_DS segment
     *          tf_esp should be the top addr of user stack (USTACKTOP)
     *          tf_eip should be the entry point of this binary program (elf->e_entry)
     *          tf_eflags should be set to enable computer to produce Interrupt
     */
    tf->tf_cs = USER_CS;
    tf->tf_ds = tf->tf_es = tf->tf_ss = USER_DS;
    tf->tf_esp = USTACKTOP;
    tf->tf_eip = elf->e_entry;
    tf->tf_eflags = FL_IF;
    ret = 0;
out:
    return ret;
bad_cleanup_mmap:
    exit_mmap(mm);
bad_elf_cleanup_pgdir:
    put_pgdir(mm);
bad_pgdir_cleanup_mm:
    mm_destroy(mm);
bad_mm:
    goto out;
}

/* copy_range - copy content of memory (start, end) of one process A to another process B
 * @to:    the addr of process B's Page Directory
 * @from:  the addr of process A's Page Directory
 * @share: flags to indicate to dup OR share. We just use dup method, so it didn't be used.
 *
 * CALL GRAPH: copy_mm-->dup_mmap-->copy_range
 */
int
copy_range(pde_t *to, pde_t *from, uintptr_t start, uintptr_t end, bool share) {
    assert(start % PGSIZE == 0 && end % PGSIZE == 0);
    assert(USER_ACCESS(start, end));
    // copy content by page unit.
    do {
        //call get_pte to find process A's pte according to the addr start
        pte_t *ptep = get_pte(from, start, 0), *nptep;
        if (ptep == NULL) {
            start = ROUNDDOWN(start + PTSIZE, PTSIZE);
            continue ;
        }
        //call get_pte to find process B's pte according to the addr start. If pte is NULL, just alloc a PT
        if (*ptep & PTE_P) {
            if ((nptep = get_pte(to, start, 1)) == NULL) {
                return -E_NO_MEM;
            }
        uint32_t perm = (*ptep & PTE_USER);
        //get page from ptep
        struct Page *page = pte2page(*ptep);
        // alloc a page for process B
        struct Page *npage=alloc_page();
        assert(page!=NULL);
        assert(npage!=NULL);
        int ret=0;
        /* LAB5:EXERCISE2
         * replicate content of page to npage, build the map of phy addr of nage with the linear addr start
         *
         * Some Useful MACROs and DEFINEs, you can use them in below implementation.
         * MACROs or Functions:
         *    page2kva(struct Page *page): return the kernel vritual addr of memory which page managed (SEE pmm.h)
         *    page_insert: build the map of phy addr of an Page with the linear addr la
         *    memcpy: typical memory copy function
         *
         * (1) find src_kvaddr: the kernel virtual address of page
         * (2) find dst_kvaddr: the kernel virtual address of npage
         * (3) memory copy from src_kvaddr to dst_kvaddr, size is PGSIZE
         * (4) build the map of phy addr of  nage with the linear addr start
         */
        void *src_kvaddr = page2kva(page);
        void *dst_kvaddr = page2kva(npage);
        memcpy(dst_kvaddr, src_kvaddr, PGSIZE);
        page_insert(to, npage, start, perm);

        assert(ret == 0);
        }
        start += PGSIZE;
    } while (start != 0 && start < end);
    return 0;
}

static void
trap_dispatch(struct trapframe *tf) {
    char c;

    int ret=0;

    switch (tf->tf_trapno) {
    case T_PGFLT:  //page fault
        if ((ret = pgfault_handler(tf)) != 0) {
            print_trapframe(tf);
            if (current == NULL) {
                panic("handle pgfault failed. ret=%d\n", ret);
            }
            else {
                if (trap_in_kernel(tf)) {
                    panic("handle pgfault failed in kernel mode. ret=%d\n", ret);
                }
                cprintf("killed by kernel.\n");
                panic("handle user mode pgfault failed. ret=%d\n", ret); 
                do_exit(-E_KILLED);
            }
        }
        break;
    case T_SYSCALL:
        syscall();
        break;
    case IRQ_OFFSET + IRQ_TIMER:
#if 0
    LAB3 : If some page replacement algorithm(such as CLOCK PRA) need tick to change the priority of pages,
    then you can add code here. 
#endif
		/* LAB1 : STEP 3 */
		/* handle the timer interrupt */
		/* (1) After a timer interrupt, you should record this event using a global variable (increase it), such as ticks in kern/driver/clock.c
		 * (2) Every TICK_NUM cycle, you can print some info using a funciton, such as print_ticks().
		 * (3) Too Simple? Yes, I think so!
		 */
		ticks = (ticks + 1) % TICK_NUM;
		if (ticks == 0)	{
			print_ticks();

        /* LAB5 */
        /* you should upate you lab1 code (just add ONE or TWO lines of code):
         *    Every TICK_NUM cycle, you should set current process's current->need_resched = 1
         */
			current->need_resched = 1;
		}
  
        break;
    case IRQ_OFFSET + IRQ_COM1:
        c = cons_getc();
        cprintf("serial [%03d] %c\n", c, c);
        break;
    case IRQ_OFFSET + IRQ_KBD:
        c = cons_getc();
        cprintf("kbd [%03d] %c\n", c, c);
        break;
    //LAB1 CHALLENGE 1 :
    case T_SWITCH_TOU:
    case T_SWITCH_TOK:
        panic("T_SWITCH_** ??\n");
        break;
    case IRQ_OFFSET + IRQ_IDE1:
    case IRQ_OFFSET + IRQ_IDE2:
        /* do nothing */
        break;
    default:
        print_trapframe(tf);
        if (current != NULL) {
            cprintf("unhandled trap.\n");
            do_exit(-E_KILLED);
        }
        // in kernel, it must be a mistake
        panic("unexpected trap in kernel.\n");
    }
}