From ab0db651af6f1ffa8fe96909ce16ae314d65c3fb Mon Sep 17 00:00:00 2001 From: Frans Kaashoek Date: Sun, 23 Sep 2018 08:24:42 -0400 Subject: 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 --- trapasm.S | 150 ++++++++++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 127 insertions(+), 23 deletions(-) (limited to 'trapasm.S') diff --git a/trapasm.S b/trapasm.S index da8aefc..b6dbb1a 100644 --- a/trapasm.S +++ b/trapasm.S @@ -1,32 +1,136 @@ +#include "param.h" +#include "x86.h" #include "mmu.h" - - # vectors.S sends all traps here. + +# vectors.S sends all traps here. .globl alltraps alltraps: # Build trap frame. - pushl %ds - pushl %es - pushl %fs - pushl %gs - pushal - - # Set up data segments. - movw $(SEG_KDATA<<3), %ax - movw %ax, %ds - movw %ax, %es + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + push %rdi + push %rsi + push %rbp + push %rdx + push %rcx + push %rbx + push %rax - # Call trap(tf), where tf=%esp - pushl %esp + cmpw $KCSEG, 32(%rsp) # compare to saved cs + jz 1f + swapgs + +1:mov %rsp, %rdi # frame in arg1 call trap - addl $4, %esp - # Return falls through to trapret... +# Return falls through to trapret... .globl trapret trapret: - popal - popl %gs - popl %fs - popl %es - popl %ds - addl $0x8, %esp # trapno and errcode - iret + cli + cmpw $KCSEG, 32(%rsp) # compare to saved cs + jz 1f + swapgs + +1:pop %rax + pop %rbx + pop %rcx + pop %rdx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + add $16, %rsp # discard trapnum and errorcode + iretq +#PAGEBREAK! + +# syscall_entry jumps here after syscall instruction +.globl sysentry +sysentry: # Build trap frame. + // load kernel stack address + swapgs + movq %rax, %gs:0 // save %rax in syscallno of cpu entry + movq %rsp, %gs:8 // user sp + movq %gs:16, %rax // proc entry + + movq %ss:0(%rax), %rax // load kstack from proc + addq $(KSTACKSIZE), %rax + + movq %rax, %rsp + movq %gs:0, %rax // restore rax + + // push usp + push $0 + push %gs:8 + // safe eflags and eip + push %r11 + push $UCSEG + push %rcx + // push errno and trapno to make stack look like a trap + push $0 + push $64 + + // push values on kernel stack + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + push %rdi + push %rsi + push %rbp + push %rdx + push %rcx + push %rbx + push %rax + + mov %rsp, %rdi # frame in arg1 + + call trap +#PAGEBREAK! + +# Return falls through to trapret... +.globl sysexit +sysexit: + # to make sure we don't get any interrupts on the user stack while in + # supervisor mode. insufficient? (see vunerability reports for sysret) + cli + + pop %rax + pop %rbx + pop %rcx + pop %rdx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + add $(5*8), %rsp # discard trapnum, errorcode, rip, cs and rflags + mov (%rsp),%rsp # switch to the user stack + swapgs + + sysretq + -- cgit v1.2.3