// Copy the mappings for shared pages into the child address space.
static int
copy_shared_pages(envid_t child)
{
// LAB 7: Your code here.
int r;
uint32_t i, j, pn;
// Copy shared address space to child
for (i = PDX(UTEXT); i < PDX(UXSTACKTOP); i++) {
if (vpd[i] & PTE_P) { // If page table present
for (j = 0; j < NPTENTRIES; j++) {
pn = PGNUM(PGADDR(i, j, 0));
if (pn == PGNUM(UXSTACKTOP - PGSIZE)) {
break; // Don't map when reach uxstack
}
if ((vpt[pn] & PTE_P) &&
(vpt[pn] & PTE_SHARE)) {
if ((r = sys_page_map(0,
(void *) (pn * PGSIZE),
child,
(void *) (pn * PGSIZE),
vpt[pn] & PTE_SYSCALL)) < 0) {
return r;
}
}
}
}
}
return 0;
}
void *umm_shmat(int shmid, void *addr, int shmflg)
{
struct shmid_ds shm;
unsigned long len;
void *mem;
int ret;
int perm;
int prot = PROT_READ;
int adjust_mmap_len = 0;
if (!(shmflg & SHM_RDONLY))
prot |= PROT_WRITE;
perm = prot_to_perm(prot);
if (shmctl(shmid, IPC_STAT, &shm) == -1)
return (void*) -1;
len = shm.shm_segsz;
if (!addr) {
if (!umm_space_left(len))
return (void*) -ENOMEM;
adjust_mmap_len = 1;
addr = (void *) umm_get_map_pos() - PGADDR(len + PGSIZE - 1);
} else if (!mem_ref_is_safe(addr, len))
return (void*) -EINVAL;
mem = shmat(shmid, addr, shmflg);
if (mem != addr)
return (void*) (long) -errno;
ret = dune_vm_map_phys(pgroot, addr, len,
(void *) dune_va_to_pa(addr),
perm);
if (ret) {
shmdt(addr);
return (void*) (long) ret;
}
if (adjust_mmap_len)
mmap_len += PGADDR(len + PGSIZE - 1);
return addr;
}
void *umm_mremap(void *old_address, size_t old_size, size_t new_size, int flags,
void *new_address)
{
int adjust_mmap_len = 0;
void *ret;
if (!mem_ref_is_safe(old_address, old_size))
return (void*) -EACCES;
if (flags & MREMAP_FIXED) {
if (!mem_ref_is_safe(new_address, new_size))
return (void*) -EACCES;
} else {
if (!umm_space_left(new_size))
return (void*) -ENOMEM;
adjust_mmap_len = 1;
new_address = (void *) umm_get_map_pos() - PGADDR(new_size + PGSIZE - 1);
}
/* XXX add support in future */
if (!(flags & MREMAP_MAYMOVE))
return (void*) -EINVAL;
flags |= MREMAP_FIXED | MREMAP_MAYMOVE;
ret = mremap(old_address, old_size, new_size, flags, new_address);
if (ret != new_address)
return (void*) (long) -errno;
if (adjust_mmap_len)
mmap_len += PGADDR(new_size + PGSIZE - 1);
dune_vm_unmap(pgroot, old_address, old_size);
if (dune_vm_map_phys(pgroot, new_address, new_size,
(void *) dune_va_to_pa(new_address),
prot_to_perm(PROT_READ | PROT_WRITE))) {
printf("help me!\n");
exit(1);
}
return ret;
}
//
// Frees env e and all memory it uses.
//
void
env_free(struct Env *e)
{
pte_t *pt;
uint32_t pdeno, pteno;
physaddr_t pa;
// If freeing the current environment, switch to boot_pgdir
// before freeing the page directory, just in case the page
// gets reused.
if (e == curenv)
lcr3(boot_cr3);
// Note the environment's demise.
// cprintf("[%08x] free env %08x\n", curenv ? curenv->env_id : 0, e->env_id);
// Flush all mapped pages in the user portion of the address space
static_assert(UTOP % PTSIZE == 0);
for (pdeno = 0; pdeno < PDX(UTOP); pdeno++) {
// only look at mapped page tables
if (!(e->env_pgdir[pdeno] & PTE_P))
continue;
// find the pa and va of the page table
pa = PTE_ADDR(e->env_pgdir[pdeno]);
pt = (pte_t*) KADDR(pa);
// unmap all PTEs in this page table
for (pteno = 0; pteno <= PTX(~0); pteno++) {
if (pt[pteno] & PTE_P)
page_remove(e->env_pgdir, PGADDR(pdeno, pteno, 0));
}
// free the page table itself
e->env_pgdir[pdeno] = 0;
page_decref(pa2page(pa));
}
// free the page directory
pa = e->env_cr3;
e->env_pgdir = 0;
e->env_cr3 = 0;
page_decref(pa2page(pa));
// return the environment to the free list
e->env_status = ENV_FREE;
LIST_INSERT_HEAD(&env_free_list, e, env_link);
}
int umm_alloc_stack(uintptr_t *stack_top)
{
int ret;
uintptr_t base = umm_get_map_pos();
if (!umm_space_left(APP_STACK_SIZE))
return -ENOMEM;
// Make sure the last page is left unmapped so hopefully
// we can at least catch most common stack overruns.
// If not, the untrusted code is only harming itself.
ret = umm_mmap_anom((void *) (PGADDR(base) -
APP_STACK_SIZE + PGSIZE),
APP_STACK_SIZE - PGSIZE,
PROT_READ | PROT_WRITE, 0);
if (ret)
return ret;
mmap_len += APP_STACK_SIZE + PGOFF(base);
*stack_top = PGADDR(base);
return 0;
}
//
// Map our virtual page pn (address pn*PGSIZE) into the target envid
// at the same virtual address. If the page is writable or copy-on-write,
// the new mapping must be created copy-on-write, and then our mapping must be
// marked copy-on-write as well. (Exercise: Why do we need to mark ours
// copy-on-write again if it was already copy-on-write at the beginning of
// this function?)
//
// Returns: 0 on success, < 0 on error.
// It is also OK to panic on error.
//
static int
duppage(envid_t envid, unsigned pn)
{
int r;
// LAB 4: Your code here.
envid_t e_id = sys_getenvid();
//cprintf("in duppage(srcenv=%d, dstenv=%d, page=%x, addr=0x%x", e_id, envid, pn, pn*PGSIZE);
void *addr = (void*) (pn * PGSIZE);
if (((uvpt[pn] & PTE_W) || (uvpt[pn] & PTE_COW)) && !(uvpt[pn] & PTE_SHARE)) {
// Make the mapping COW
//cprintf("-------COW\n");
int mapping_err;
mapping_err = sys_page_map(e_id, addr, envid, addr, PTE_P | PTE_COW | PTE_U);
if (mapping_err) {
panic("mapping other environment's page to current env failed");
}
// mapping_err = sys_page_unmap(e_id, addr);
// if (mapping_err) {
// panic("unmapping environment's page to self failed");
// }
mapping_err = sys_page_map(envid, addr, e_id, addr, PTE_P | PTE_COW | PTE_U);
if (mapping_err) {
panic("dst mapping back to src failed with error %e", mapping_err);
}
} else {
// Normal mapping
//cprintf("-------NORMAL\n");
sys_page_map(0, PGADDR(0, pn, 0),
envid, PGADDR(0, pn, 0),
(uvpt[pn] & PTE_SYSCALL));
// sys_page_map(e_id, addr, envid, addr, PTE_P | PTE_U);
}
return 0;
}
unsigned long umm_mmap(void *addr, size_t len, int prot,
int flags, int fd, off_t offset)
{
int adjust_mmap_len = 0;
int ret;
#if USE_BIG_MEM
if (len >= BIG_PGSIZE && (flags & MAP_ANONYMOUS) && !addr)
return umm_map_big(len, prot);
#endif
if (!addr) {
if (!umm_space_left(len))
return -ENOMEM;
adjust_mmap_len = 1;
addr = (void *) umm_get_map_pos() - PGADDR(len + PGSIZE - 1);
} else if (!mem_ref_is_safe(addr, len))
return -EINVAL;
if (flags & MAP_ANONYMOUS) {
ret = umm_mmap_anom(addr, len, prot, 0);
if (ret)
return ret;
} else if (fd > 0) {
ret = umm_mmap_file(addr, len, prot, flags, fd, offset);
if (ret)
return ret;
} else
return -EINVAL;
if (adjust_mmap_len)
mmap_len += PGADDR(len + PGSIZE - 1);
return (unsigned long) addr;
}
unsigned long umm_brk(unsigned long brk)
{
size_t len;
int ret;
if (!brk)
return UMM_ADDR_START;
if (brk < UMM_ADDR_START)
return -EINVAL;
len = brk - UMM_ADDR_START;
#if USE_BIG_MEM
len = BIG_PGADDR(len + BIG_PGSIZE - 1);
#else
len = PGADDR(len + PGSIZE - 1);
#endif
if (!umm_space_left(len))
return -ENOMEM;
if (len == brk_len) {
return brk;
} else if (len < brk_len) {
ret = munmap((void *) (UMM_ADDR_START + len), brk_len - len);
if (ret)
return -errno;
dune_vm_unmap(pgroot, (void *) (UMM_ADDR_START + len),
brk_len - len);
} else {
ret = umm_mmap_anom((void *) (UMM_ADDR_START + brk_len),
len - brk_len,
PROT_READ | PROT_WRITE, USE_BIG_MEM);
if (ret)
return ret;
}
brk_len = len;
return brk;
}
void dune_vm_default_pgflt_handler(uintptr_t addr, uint64_t fec)
{
ptent_t *pte = NULL;
int rc;
/*
* Assert on present and reserved bits.
*/
assert(!(fec & (FEC_P | FEC_RSV)));
rc = dune_vm_lookup(pgroot, (void *) addr, 0, &pte);
assert(rc == 0);
if ((fec & FEC_W) && (*pte & PTE_COW)) {
void *newPage;
struct page *pg = dune_pa2page(PTE_ADDR(*pte));
ptent_t perm = PTE_FLAGS(*pte);
// Compute new permissions
perm &= ~PTE_COW;
perm |= PTE_W;
if (dune_page_isfrompool(PTE_ADDR(*pte)) && pg->ref == 1) {
*pte = PTE_ADDR(*pte) | perm;
return;
}
// Duplicate page
newPage = alloc_page();
memcpy(newPage, (void *)PGADDR(addr), PGSIZE);
// Map page
if (dune_page_isfrompool(PTE_ADDR(*pte))) {
dune_page_put(pg);
}
*pte = PTE_ADDR(newPage) | perm;
// Invalidate
dune_flush_tlb_one(addr);
}
}
//
// Initialize page structure and memory free list.
// After this is done, NEVER use boot_alloc again. ONLY use the page
// allocator functions below to allocate and deallocate physical
// memory via the page_free_list.
//
void
page_init(void)
{
// The example code here marks all physical pages as free.
// However this is not truly the case. What memory is free?
// 1) Mark physical page 0 as in use.
// This way we preserve the real-mode IDT and BIOS structures
// in case we ever need them. (Currently we don't, but...)
// 2) The rest of base memory, [PGSIZE, npages_basemem * PGSIZE)
// is free.
// 3) Then comes the IO hole [IOPHYSMEM, EXTPHYSMEM), which must
// never be allocated.
// 4) Then extended memory [EXTPHYSMEM, ...).
// Some of it is in use, some is free. Where is the kernel
// in physical memory? Which pages are already in use for
// page tables and other data structures?
//
// Change the code to reflect this.
// NB: DO NOT actually touch the physical memory corresponding to
// free pages!
int i;
physaddr_t firstFreePhysAddr=(physaddr_t)PADDR(boot_alloc(0));
page_free_list=NULL;
for (i = npages-1; i >= 0; i--)
{
physaddr_t pagePhysAddr=(physaddr_t)PGADDR(0,i,0);
if(pagePhysAddr==0||
(pagePhysAddr>=IOPHYSMEM&&pagePhysAddr<firstFreePhysAddr))
{
pages[i].pp_ref=1;
pages[i].pp_link=NULL;
}
else
{
pages[i].pp_ref=0;
pages[i].pp_link=page_free_list;
page_free_list=&pages[i];
}
}
}
/* *
* The page directory entry corresponding to the virtual address range
* [VPT, VPT + PTSIZE) points to the page directory itself. Thus, the page
* directory is treated as a page table as well as a page directory.
*
* One result of treating the page directory as a page table is that all PTEs
* can be accessed though a "virtual page table" at virtual address VPT. And the
* PTE for number n is stored in vpt[n].
*
* A second consequence is that the contents of the current page directory will
* always available at virtual address PGADDR(PDX(VPT), PDX(VPT), 0), to which
* vpd is set bellow.
* */
pte_t * const vpt = (pte_t *)VPT;
pde_t * const vpd = (pde_t *)PGADDR(PDX(VPT), PDX(VPT), 0);
/* *
* Global Descriptor Table:
*
* The kernel and user segments are identical (except for the DPL). To load
* the %ss register, the CPL must equal the DPL. Thus, we must duplicate the
* segments for the user and the kernel. Defined as follows:
* - 0x0 : unused (always faults -- for trapping NULL far pointers)
* - 0x8 : kernel code segment
* - 0x10: kernel data segment
* - 0x18: user code segment
* - 0x20: user data segment
* - 0x28: defined for tss, initialized in gdt_init
* */
static struct segdesc gdt[] = {
// Spawn a child process from a program image loaded from the file system.
// prog: the pathname of the program to run.
// argv: pointer to null-terminated array of pointers to strings,
// which will be passed to the child as its command-line arguments.
// Returns child envid on success, < 0 on failure.
int
spawn(const char *prog, const char **argv)
{
unsigned char elf_buf[512];
struct Trapframe child_tf;
envid_t child;
// Insert your code, following approximately this procedure:
//
// - Open the program file.
//
// - Read the ELF header, as you have before, and sanity check its
// magic number. (Check out your load_icode!)
//
// - Use sys_exofork() to create a new environment.
//
// - Set child_tf to an initial struct Trapframe for the child.
// Hint: The sys_exofork() system call has already created
// a good basis, in envs[ENVX(child)].env_tf.
// Hint: You must do something with the program's entry point.
// What? (See load_icode!)
//
// - Call the init_stack() function above to set up
// the initial stack page for the child environment.
//
// - Map all of the program's segments that are of p_type
// ELF_PROG_LOAD into the new environment's address space.
// Use the p_flags field in the Proghdr for each segment
// to determine how to map the segment:
//
// * If the ELF flags do not include ELF_PROG_FLAG_WRITE,
// then the segment contains text and read-only data.
// Use read_map() to read the contents of this segment,
// and map the pages it returns directly into the child
// so that multiple instances of the same program
// will share the same copy of the program text.
// Be sure to map the program text read-only in the child.
// Read_map is like read but returns a pointer to the data in
// *blk rather than copying the data into another buffer.
//
// * If the ELF segment flags DO include ELF_PROG_FLAG_WRITE,
// then the segment contains read/write data and bss.
// As with load_icode() in Lab 3, such an ELF segment
// occupies p_memsz bytes in memory, but only the FIRST
// p_filesz bytes of the segment are actually loaded
// from the executable file - you must clear the rest to zero.
// For each page to be mapped for a read/write segment,
// allocate a page in the parent temporarily at UTEMP,
// read() the appropriate portion of the file into that page
// and/or use memset() to zero non-loaded portions.
// (You can avoid calling memset(), if you like, if
// page_alloc() returns zeroed pages already.)
// Then insert the page mapping into the child.
// Look at init_stack() for inspiration.
// Be sure you understand why you can't use read_map() here.
//
// Note: None of the segment addresses or lengths above
// are guaranteed to be page-aligned, so you must deal with
// these non-page-aligned values appropriately.
// The ELF linker does, however, guarantee that no two segments
// will overlap on the same page; and it guarantees that
// PGOFF(ph->p_offset) == PGOFF(ph->p_va).
//
// - Call sys_env_set_trapframe(child, &child_tf) to set up the
// correct initial eip and esp values in the child.
//
// - Start the child process running with sys_env_set_status().
// LAB 5: Your code here.
int fdnum;
struct Elf *elf;
char elfbuf[512];
uintptr_t init_esp;
int r;
struct Proghdr *ph, *eph;
uint32_t pageva,pageoff;
void *blk;
uint32_t i;
uint32_t left;
uint32_t pteno,pdeno;
uint32_t pn = 0;
uintptr_t addr;
pte_t pte;
//cprintf("spawn:%s\n",prog);
if((fdnum = open(prog, O_RDWR)) < 0)
return fdnum;
read(fdnum, elfbuf, 512);
elf = (struct Elf *) elfbuf;
if(elf->e_magic != ELF_MAGIC)
return -E_NOT_EXEC;
if((child = sys_exofork()) < 0)
return child;
else if(child == 0)
{
//cprintf("child\n");
env = &envs[ENVX(sys_getenvid())];
return 0;
}
child_tf = envs[ENVX(child)].env_tf;
child_tf.tf_eip = elf->e_entry;
if((r = init_stack(child, argv, &init_esp)) < 0)
return r;
child_tf.tf_esp = init_esp;
ph = (struct Proghdr *) ((uint8_t*)elf + elf->e_phoff);
eph = ph + elf->e_phnum;
for (; ph != eph; ph++)
{
if(ph->p_type == ELF_PROG_LOAD)
{
pageva = ROUNDDOWN(ph->p_va, PGSIZE);
pageoff = ROUNDDOWN(ph->p_offset, PGSIZE);
if(!(ph->p_flags & ELF_PROG_FLAG_WRITE))
{
for(i = 0; i< ph->p_memsz; i += PGSIZE)
{
if((r = read_map(fdnum, pageoff + i,&blk)) < 0)
return r;
if((r = sys_page_map(0, blk, child, (void *)(pageva + i),PTE_U|PTE_P)) < 0)
return r;
}
}
else
{
for(i = 0; i < ph->p_memsz; i += PGSIZE)
{
sys_page_alloc(0, (void*)UTEMP, PTE_U|PTE_P|PTE_W);
if( i < ph->p_filesz)
{
seek(fdnum, pageoff + i);
left = ph->p_filesz - i;
if(left > PGSIZE)
read(fdnum, (void *)UTEMP, PGSIZE);
else
{
read(fdnum,(void *)UTEMP, left);
memset((void*)(UTEMP + left),0x0,PGSIZE - left);
}
}
else
memset((void*)UTEMP, 0x0,PGSIZE);
sys_page_map(0, UTEMP, child,(void *)(pageva + i),PTE_U|PTE_W|PTE_P);
sys_page_unmap(0,UTEMP);
}
}
}
}
close(fdnum);
if((r = sys_env_set_trapframe(child, &child_tf)) < 0)
return r;
for(pdeno = PDX(0);pdeno < PDX(UTOP);pdeno++)
{
if(!(vpd[pdeno] & (PTE_P)))
continue;
else
{
for(pteno = 0;pteno < NPTENTRIES;pteno++)
{
pn = (pdeno<<10) + pteno;
if((vpt[pn] & PTE_P) && (vpt[pn] & PTE_SHARE))
{
//remember not to modify vpt[pn]
pte = vpt[pn] & PTE_USER;
addr = (uintptr_t)PGADDR(pdeno, pteno, 0);
sys_page_map(0,(void*)addr,child,(void*)addr,pte);
}
}
}
}
if((r = sys_env_set_status(child, ENV_RUNNABLE)) < 0)
return r;
return child;
//panic("spawn unimplemented!");
}