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
126 lines
2.8 KiB
C
126 lines
2.8 KiB
C
// Mutual exclusion spin locks.
|
|
|
|
#include "types.h"
|
|
#include "defs.h"
|
|
#include "param.h"
|
|
#include "x86.h"
|
|
#include "memlayout.h"
|
|
#include "mmu.h"
|
|
#include "proc.h"
|
|
#include "spinlock.h"
|
|
|
|
void
|
|
initlock(struct spinlock *lk, char *name)
|
|
{
|
|
lk->name = name;
|
|
lk->locked = 0;
|
|
lk->cpu = 0;
|
|
}
|
|
|
|
// Acquire the lock.
|
|
// Loops (spins) until the lock is acquired.
|
|
// Holding a lock for a long time may cause
|
|
// other CPUs to waste time spinning to acquire it.
|
|
void
|
|
acquire(struct spinlock *lk)
|
|
{
|
|
pushcli(); // disable interrupts to avoid deadlock.
|
|
if(holding(lk))
|
|
panic("acquire");
|
|
|
|
// The xchg is atomic.
|
|
while(xchg(&lk->locked, 1) != 0)
|
|
;
|
|
|
|
// Tell the C compiler and the processor to not move loads or stores
|
|
// past this point, to ensure that the critical section's memory
|
|
// references happen after the lock is acquired.
|
|
__sync_synchronize();
|
|
|
|
// Record info about lock acquisition for debugging.
|
|
lk->cpu = mycpu();
|
|
getcallerpcs(&lk, lk->pcs);
|
|
}
|
|
|
|
// Release the lock.
|
|
void
|
|
release(struct spinlock *lk)
|
|
{
|
|
if(!holding(lk))
|
|
panic("release");
|
|
|
|
lk->pcs[0] = 0;
|
|
lk->cpu = 0;
|
|
|
|
// Tell the C compiler and the processor to not move loads or stores
|
|
// past this point, to ensure that all the stores in the critical
|
|
// section are visible to other cores before the lock is released.
|
|
// Both the C compiler and the hardware may re-order loads and
|
|
// stores; __sync_synchronize() tells them both not to.
|
|
__sync_synchronize();
|
|
|
|
// Release the lock, equivalent to lk->locked = 0.
|
|
// This code can't use a C assignment, since it might
|
|
// not be atomic. A real OS would use C atomics here.
|
|
asm volatile("movl $0, %0" : "+m" (lk->locked) : );
|
|
|
|
popcli();
|
|
}
|
|
|
|
// Record the current call stack in pcs[] by following the %ebp chain.
|
|
void
|
|
getcallerpcs(void *v, uint64 pcs[])
|
|
{
|
|
uint64 *ebp;
|
|
int i;
|
|
|
|
asm volatile("mov %%rbp, %0" : "=r" (ebp));
|
|
for(i = 0; i < 10; i++){
|
|
if(ebp == 0 || ebp < (uint64*)KERNBASE || ebp == (uint64*)0xffffffff)
|
|
break;
|
|
pcs[i] = ebp[1]; // saved %eip
|
|
ebp = (uint64*)ebp[0]; // saved %ebp
|
|
}
|
|
for(; i < 10; i++)
|
|
pcs[i] = 0;
|
|
}
|
|
|
|
// Check whether this cpu is holding the lock.
|
|
int
|
|
holding(struct spinlock *lock)
|
|
{
|
|
int r;
|
|
pushcli();
|
|
r = lock->locked && lock->cpu == mycpu();
|
|
popcli();
|
|
return r;
|
|
}
|
|
|
|
|
|
// Pushcli/popcli are like cli/sti except that they are matched:
|
|
// it takes two popcli to undo two pushcli. Also, if interrupts
|
|
// are off, then pushcli, popcli leaves them off.
|
|
|
|
void
|
|
pushcli(void)
|
|
{
|
|
int eflags;
|
|
|
|
eflags = readeflags();
|
|
cli();
|
|
if(mycpu()->ncli == 0)
|
|
mycpu()->intena = eflags & FL_IF;
|
|
mycpu()->ncli += 1;
|
|
}
|
|
|
|
void
|
|
popcli(void)
|
|
{
|
|
if(readeflags()&FL_IF)
|
|
panic("popcli - interruptible");
|
|
if(--mycpu()->ncli < 0)
|
|
panic("popcli");
|
|
if(mycpu()->ncli == 0 && mycpu()->intena)
|
|
sti();
|
|
}
|
|
|