Checkpoint port of xv6 to x86-64. Passed usertests on 2 processors a few times.

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

1 files changed, 16 insertions, 18 deletions

diff --git a/proc.c b/proc.c
index 806b1b1..58ae948 100644
--- a/proc.c
+++ b/proc.c
@@ -6,6 +6,7 @@
 #include "x86.h"
 #include "proc.h"
 #include "spinlock.h"
+#include "msr.h"
 
 struct {
   struct spinlock lock;
@@ -16,7 +17,7 @@ static struct proc *initproc;
 
 int nextpid = 1;
 extern void forkret(void);
-extern void trapret(void);
+extern void sysexit(void);
 
 static void wakeup1(void *chan);
 
@@ -104,13 +105,13 @@ found:
 
   // Set up new context to start executing at forkret,
   // which returns to trapret.
-  sp -= 4;
-  *(uint*)sp = (uint)trapret;
+  sp -= sizeof(uint64);
+  *(uint64*)sp = (uint64)sysexit;
 
   sp -= sizeof *p->context;
   p->context = (struct context*)sp;
   memset(p->context, 0, sizeof *p->context);
-  p->context->eip = (uint)forkret;
+  p->context->eip = (uint64)forkret;
 
   return p;
 }
@@ -128,16 +129,12 @@ userinit(void)
   initproc = p;
   if((p->pgdir = setupkvm()) == 0)
     panic("userinit: out of memory?");
-  inituvm(p->pgdir, _binary_initcode_start, (int)_binary_initcode_size);
+  inituvm(p->pgdir, _binary_initcode_start, (uint64)_binary_initcode_size);
   p->sz = PGSIZE;
   memset(p->tf, 0, sizeof(*p->tf));
-  p->tf->cs = (SEG_UCODE << 3) | DPL_USER;
-  p->tf->ds = (SEG_UDATA << 3) | DPL_USER;
-  p->tf->es = p->tf->ds;
-  p->tf->ss = p->tf->ds;
-  p->tf->eflags = FL_IF;
-  p->tf->esp = PGSIZE;
-  p->tf->eip = 0;  // beginning of initcode.S
+  p->tf->r11 = FL_IF;
+  p->tf->rsp = PGSIZE;
+  p->tf->rcx = 0;  // beginning of initcode.S
 
   safestrcpy(p->name, "initcode", sizeof(p->name));
   p->cwd = namei("/");
@@ -201,7 +198,7 @@ fork(void)
   *np->tf = *curproc->tf;
 
   // Clear %eax so that fork returns 0 in the child.
-  np->tf->eax = 0;
+  np->tf->rax = 0;
 
   for(i = 0; i < NOFILE; i++)
     if(curproc->ofile[i])
@@ -289,8 +286,8 @@ wait(void)
         pid = p->pid;
         kfree(p->kstack);
         p->kstack = 0;
-        freevm(p->pgdir);
-        p->pid = 0;
+        freevm(p->pgdir, p->sz);
+         p->pid = 0;
         p->parent = 0;
         p->name[0] = 0;
         p->killed = 0;
@@ -339,6 +336,7 @@ scheduler(void)
       // Switch to chosen process.  It is the process's job
       // to release ptable.lock and then reacquire it
       // before jumping back to us.
+
       c->proc = p;
       switchuvm(p);
       p->state = RUNNING;
@@ -408,7 +406,7 @@ forkret(void)
     iinit(ROOTDEV);
     initlog(ROOTDEV);
   }
-
+  
   // Return to "caller", actually trapret (see allocproc).
 }
 
@@ -514,7 +512,7 @@ procdump(void)
   int i;
   struct proc *p;
   char *state;
-  uint pc[10];
+  uint64 pc[10];
 
   for(p = ptable.proc; p < &ptable.proc[NPROC]; p++){
     if(p->state == UNUSED)
@@ -525,7 +523,7 @@ procdump(void)
       state = "???";
     cprintf("%d %s %s", p->pid, state, p->name);
     if(p->state == SLEEPING){
-      getcallerpcs((uint*)p->context->ebp+2, pc);
+      getcallerpcs((uint64*)p->context->ebp+2, pc);
       for(i=0; i<10 && pc[i] != 0; i++)
         cprintf(" %p", pc[i]);
     }