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
120 lines
2.7 KiB
C
120 lines
2.7 KiB
C
#include "types.h"
|
|
#include "param.h"
|
|
#include "memlayout.h"
|
|
#include "mmu.h"
|
|
#include "proc.h"
|
|
#include "defs.h"
|
|
#include "traps.h"
|
|
#include "msr.h"
|
|
#include "x86.h"
|
|
#include "elf.h"
|
|
|
|
int
|
|
exec(char *path, char **argv)
|
|
{
|
|
char *s, *last;
|
|
int i, off;
|
|
uint64 argc, sz, sp, ustack[3+MAXARG+1];
|
|
struct elfhdr elf;
|
|
struct inode *ip;
|
|
struct proghdr ph;
|
|
pde_t *pgdir, *oldpgdir;
|
|
struct proc *curproc = myproc();
|
|
uint64 oldsz = curproc->sz;
|
|
|
|
begin_op();
|
|
|
|
if((ip = namei(path)) == 0){
|
|
end_op();
|
|
return -1;
|
|
}
|
|
ilock(ip);
|
|
pgdir = 0;
|
|
|
|
// Check ELF header
|
|
if(readi(ip, (char*)&elf, 0, sizeof(elf)) != sizeof(elf))
|
|
goto bad;
|
|
if(elf.magic != ELF_MAGIC)
|
|
goto bad;
|
|
|
|
if((pgdir = setupkvm()) == 0)
|
|
goto bad;
|
|
|
|
// Load program into memory.
|
|
sz = 0;
|
|
for(i=0, off=elf.phoff; i<elf.phnum; i++, off+=sizeof(ph)){
|
|
if(readi(ip, (char*)&ph, off, sizeof(ph)) != sizeof(ph))
|
|
goto bad;
|
|
if(ph.type != ELF_PROG_LOAD)
|
|
continue;
|
|
if(ph.memsz < ph.filesz)
|
|
goto bad;
|
|
if(ph.vaddr + ph.memsz < ph.vaddr)
|
|
goto bad;
|
|
if((sz = allocuvm(pgdir, sz, ph.vaddr + ph.memsz)) == 0)
|
|
goto bad;
|
|
if(ph.vaddr % PGSIZE != 0)
|
|
goto bad;
|
|
if(loaduvm(pgdir, (char*)ph.vaddr, ip, ph.off, ph.filesz) < 0)
|
|
goto bad;
|
|
}
|
|
iunlockput(ip);
|
|
end_op();
|
|
ip = 0;
|
|
|
|
// Allocate two pages at the next page boundary.
|
|
// Make the first inaccessible. Use the second as the user stack.
|
|
sz = PGROUNDUP(sz);
|
|
if((sz = allocuvm(pgdir, sz, sz + 2*PGSIZE)) == 0)
|
|
goto bad;
|
|
clearpteu(pgdir, (char*)(sz - 2*PGSIZE));
|
|
sp = sz;
|
|
|
|
// Push argument strings, prepare rest of stack in ustack.
|
|
for(argc = 0; argv[argc]; argc++) {
|
|
if(argc >= MAXARG)
|
|
goto bad;
|
|
sp = (sp - (strlen(argv[argc]) + 1)) & ~(sizeof(uint64)-1);
|
|
if(copyout(pgdir, sp, argv[argc], strlen(argv[argc]) + 1) < 0)
|
|
goto bad;
|
|
ustack[3+argc] = sp;
|
|
}
|
|
ustack[3+argc] = 0;
|
|
|
|
ustack[0] = 0xffffffff; // fake return PC
|
|
ustack[1] = argc;
|
|
ustack[2] = sp - (argc+1)*sizeof(uint64); // argv pointer
|
|
|
|
curproc->tf->rdi = argc;
|
|
curproc->tf->rsi = sp - (argc+1)*sizeof(uint64);
|
|
|
|
sp -= (3+argc+1) * sizeof(uint64);
|
|
if(copyout(pgdir, sp, ustack, (3+argc+1)*sizeof(uint64)) < 0)
|
|
goto bad;
|
|
|
|
// Save program name for debugging.
|
|
for(last=s=path; *s; s++)
|
|
if(*s == '/')
|
|
last = s+1;
|
|
safestrcpy(curproc->name, last, sizeof(curproc->name));
|
|
|
|
// Commit to the user image.
|
|
oldpgdir = curproc->pgdir;
|
|
curproc->pgdir = pgdir;
|
|
curproc->sz = sz;
|
|
curproc->tf->rip = elf.entry; // main
|
|
curproc->tf->rcx = elf.entry;
|
|
curproc->tf->rsp = sp;
|
|
switchuvm(curproc);
|
|
freevm(oldpgdir, oldsz);
|
|
return 0;
|
|
|
|
bad:
|
|
if(pgdir)
|
|
freevm(pgdir, sz);
|
|
if(ip){
|
|
iunlockput(ip);
|
|
end_op();
|
|
}
|
|
return -1;
|
|
}
|