ab0db651af
The x86-64 doesn't just add two levels to page tables to support 64 bit addresses, but is a different processor. For example, calling conventions, system calls, and segmentation are different from 32-bit x86. Segmentation is basically gone, but gs/fs in combination with MSRs can be used to hold a per-core pointer. In general, x86-64 is more straightforward than 32-bit x86. The port uses code from sv6 and the xv6 "rsc-amd64" branch. A summary of the changes is as follows: - Booting: switch to grub instead of xv6's bootloader (pass -kernel to qemu), because xv6's boot loader doesn't understand 64bit ELF files. And, we don't care anymore about booting. - Makefile: use -m64 instead of -m32 flag for gcc, delete boot loader, xv6.img, bochs, and memfs. For now dont' use -O2, since usertests with -O2 is bigger than MAXFILE! - Update gdb.tmpl to be for i386 or x86-64 - Console/printf: use stdarg.h and treat 64-bit addresses different from ints (32-bit) - Update elfhdr to be 64 bit - entry.S/entryother.S: add code to switch to 64-bit mode: build a simple page table in 32-bit mode before switching to 64-bit mode, share code for entering boot processor and APs, and tweak boot gdt. The boot gdt is the gdt that the kernel proper also uses. (In 64-bit mode, the gdt/segmentation and task state mostly disappear.) - exec.c: fix passing argv (64-bit now instead of 32-bit). - initcode.c: use syscall instead of int. - kernel.ld: load kernel very high, in top terabyte. 64 bits is a lot of address space! - proc.c: initial return is through new syscall path instead of trapret. - proc.h: update struct cpu to have some scratch space since syscall saves less state than int, update struct context to reflect x86-64 calling conventions. - swtch: simplify for x86-64 calling conventions. - syscall: add fetcharg to handle x86-64 calling convetions (6 arguments are passed through registers), and fetchaddr to read a 64-bit value from user space. - sysfile: update to handle pointers from user space (e.g., sys_exec), which are 64 bits. - trap.c: no special trap vector for sys calls, because x86-64 has a different plan for system calls. - trapasm: one plan for syscalls and one plan for traps (interrupt and exceptions). On x86-64, the kernel is responsible for switching user/kernel stacks. To do, xv6 keeps some scratch space in the cpu structure, and uses MSR GS_KERN_BASE to point to the core's cpu structure (using swapgs). - types.h: add uint64, and change pde_t to uint64 - usertests: exit() when fork fails, which helped in tracking down one of the bugs in the switch from 32-bit to 64-bit - vectors: update to make them 64 bits - vm.c: use bootgdt in kernel too, program MSRs for syscalls and core-local state (for swapgs), walk 4 levels in walkpgdir, add DEVSPACETOP, use task segment to set kernel stack for interrupts (but simpler than in 32-bit mode), add an extra argument to freevm (size of user part of address space) to avoid checking all entries till KERNBASE (there are MANY TB before the top 1TB). - x86: update trapframe to have 64-bit entries, which is what the processor pushes on syscalls and traps. simplify lgdt and lidt, using struct desctr, which needs the gcc directives packed and aligned. TODO: - use int32 instead of int? - simplify curproc(). xv6 has per-cpu state again, but this time it must have it. - avoid repetition in walkpgdir - fix validateint() in usertests.c - fix bugs (e.g., observed one a case of entering kernel with invalid gs or proc
185 lines
4 KiB
C
185 lines
4 KiB
C
#include "types.h"
|
|
#include "defs.h"
|
|
#include "param.h"
|
|
#include "memlayout.h"
|
|
#include "mmu.h"
|
|
#include "proc.h"
|
|
#include "x86.h"
|
|
#include "syscall.h"
|
|
|
|
// User code makes a system call with INT T_SYSCALL.
|
|
// System call number in %eax.
|
|
// Arguments on the stack, from the user call to the C
|
|
// library system call function. The saved user %esp points
|
|
// to a saved program counter, and then the first argument.
|
|
|
|
// Fetch the int at addr from the current process.
|
|
int
|
|
fetchint(uint64 addr, int *ip)
|
|
{
|
|
struct proc *curproc = myproc();
|
|
|
|
if(addr >= curproc->sz || addr+4 > curproc->sz)
|
|
return -1;
|
|
*ip = *(uint64*)(addr);
|
|
return 0;
|
|
}
|
|
|
|
// Fetch the nul-terminated string at addr from the current process.
|
|
// Doesn't actually copy the string - just sets *pp to point at it.
|
|
// Returns length of string, not including nul.
|
|
int
|
|
fetchstr(uint64 addr, char **pp)
|
|
{
|
|
char *s, *ep;
|
|
struct proc *curproc = myproc();
|
|
|
|
if(addr >= curproc->sz)
|
|
return -1;
|
|
*pp = (char*)addr;
|
|
ep = (char*)curproc->sz;
|
|
for(s = *pp; s < ep; s++){
|
|
if(*s == 0)
|
|
return s - *pp;
|
|
}
|
|
return -1;
|
|
}
|
|
|
|
static uint64
|
|
fetcharg(int n)
|
|
{
|
|
struct proc *curproc = myproc();
|
|
switch (n) {
|
|
case 0:
|
|
return curproc->tf->rdi;
|
|
case 1:
|
|
return curproc->tf->rsi;
|
|
case 2:
|
|
return curproc->tf->rdx;
|
|
case 3:
|
|
return curproc->tf->r10;
|
|
case 4:
|
|
return curproc->tf->r8;
|
|
case 5:
|
|
return curproc->tf->r9;
|
|
}
|
|
panic("fetcharg");
|
|
return -1;
|
|
}
|
|
|
|
int
|
|
fetchaddr(uint64 addr, uint64 *ip)
|
|
{
|
|
struct proc *curproc = myproc();
|
|
if(addr >= curproc->sz || addr+sizeof(uint64) > curproc->sz)
|
|
return -1;
|
|
*ip = *(uint64*)(addr);
|
|
return 0;
|
|
}
|
|
|
|
// Fetch the nth 32-bit system call argument.
|
|
int
|
|
argint(int n, int *ip)
|
|
{
|
|
*ip = fetcharg(n);
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
argaddr(int n, uint64 *ip)
|
|
{
|
|
*ip = fetcharg(n);
|
|
return 0;
|
|
}
|
|
|
|
// Fetch the nth word-sized system call argument as a pointer
|
|
// to a block of memory of size bytes. Check that the pointer
|
|
// lies within the process address space.
|
|
int
|
|
argptr(int n, char **pp, int size)
|
|
{
|
|
uint64 i;
|
|
struct proc *curproc = myproc();
|
|
|
|
if(argaddr(n, &i) < 0)
|
|
return -1;
|
|
if(size < 0 || (uint)i >= curproc->sz || (uint)i+size > curproc->sz)
|
|
return -1;
|
|
*pp = (char*)i;
|
|
return 0;
|
|
}
|
|
|
|
// Fetch the nth word-sized system call argument as a string pointer.
|
|
// Check that the pointer is valid and the string is nul-terminated.
|
|
// (There is no shared writable memory, so the string can't change
|
|
// between this check and being used by the kernel.)
|
|
int
|
|
argstr(int n, char **pp)
|
|
{
|
|
int addr;
|
|
if(argint(n, &addr) < 0)
|
|
return -1;
|
|
return fetchstr(addr, pp);
|
|
}
|
|
|
|
extern int sys_chdir(void);
|
|
extern int sys_close(void);
|
|
extern int sys_dup(void);
|
|
extern int sys_exec(void);
|
|
extern int sys_exit(void);
|
|
extern int sys_fork(void);
|
|
extern int sys_fstat(void);
|
|
extern int sys_getpid(void);
|
|
extern int sys_kill(void);
|
|
extern int sys_link(void);
|
|
extern int sys_mkdir(void);
|
|
extern int sys_mknod(void);
|
|
extern int sys_open(void);
|
|
extern int sys_pipe(void);
|
|
extern int sys_read(void);
|
|
extern int sys_sbrk(void);
|
|
extern int sys_sleep(void);
|
|
extern int sys_unlink(void);
|
|
extern int sys_wait(void);
|
|
extern int sys_write(void);
|
|
extern int sys_uptime(void);
|
|
|
|
static int (*syscalls[])(void) = {
|
|
[SYS_fork] sys_fork,
|
|
[SYS_exit] sys_exit,
|
|
[SYS_wait] sys_wait,
|
|
[SYS_pipe] sys_pipe,
|
|
[SYS_read] sys_read,
|
|
[SYS_kill] sys_kill,
|
|
[SYS_exec] sys_exec,
|
|
[SYS_fstat] sys_fstat,
|
|
[SYS_chdir] sys_chdir,
|
|
[SYS_dup] sys_dup,
|
|
[SYS_getpid] sys_getpid,
|
|
[SYS_sbrk] sys_sbrk,
|
|
[SYS_sleep] sys_sleep,
|
|
[SYS_uptime] sys_uptime,
|
|
[SYS_open] sys_open,
|
|
[SYS_write] sys_write,
|
|
[SYS_mknod] sys_mknod,
|
|
[SYS_unlink] sys_unlink,
|
|
[SYS_link] sys_link,
|
|
[SYS_mkdir] sys_mkdir,
|
|
[SYS_close] sys_close,
|
|
};
|
|
|
|
void
|
|
syscall(void)
|
|
{
|
|
int num;
|
|
struct proc *curproc = myproc();
|
|
|
|
num = curproc->tf->rax;
|
|
if(num > 0 && num < NELEM(syscalls) && syscalls[num]) {
|
|
curproc->tf->rax = syscalls[num]();
|
|
} else {
|
|
cprintf("%d %s: unknown sys call %d\n",
|
|
curproc->pid, curproc->name, num);
|
|
curproc->tf->rax = -1;
|
|
}
|
|
}
|