fpu: save each process's x87/SSE registers; keep the kernel off them

Nothing ever saved the FPU and SSE registers on a context switch.
musl's memcpy, the compiler's struct copies and any arithmetic on
doubles keep live values in %xmm, so two processes sharing a CPU wrote
over each other's: two shells counting in a loop on one processor took
a NULL+8 page fault within seconds, at a different rip every time. It
reproduces on kernels from before this week too -- it had always been
there, and every crash nobody could explain was a candidate.

sched() now fxsaves the process leaving the CPU and scheduler()
fxrstors the one arriving. A new process starts from the ABI's state
(FCW 0x37F, MXCSR 0x1F80), fork copies the parent's live registers,
exec resets them, and a signal handler's are put back by rt_sigreturn
so the interrupted code finds what it had.

The kernel was free to use %xmm too -- GCC vectorised struct copies
and memset into 153 instructions of it -- so an interrupt could
clobber the registers of the program it interrupted with no switch at
all. Kernel, lwIP and uACPI objects are built -mgeneral-regs-only now
and the image has none; cmd/ keeps SSE.

Checked under QEMU: three concurrent loops three times over, on 1 CPU
and on 4, no faults; before, every run faulted.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S1giNvrHTrPMPw7V6x1kQ4
This commit is contained in:
Nexoniarz 2026-10-23 15:02:01 +02:00
commit 0e39e711f1
6 changed files with 69 additions and 0 deletions

View file

@ -2,6 +2,7 @@
#include "defs.h"
#include "param.h"
#include "proc.h"
#include "x86.h"
#include "syscall.h"
#include "uaccess.h"
#include "errno.h"
@ -131,6 +132,7 @@ sys_rt_sigreturn(void)
{
addr_t saved_rax = myproc()->saved_sigtf.rax;
*myproc()->tf = myproc()->saved_sigtf;
fxrstor(myproc()->sigfpu); // what the interrupted code had
myproc()->in_signal = 0;
// If this handler interrupted a sigsuspend(), put its pre-suspend
// signal mask back now that the handler has finished.
@ -226,6 +228,9 @@ deliver_signals(struct trapframe *tf)
myproc()->pending_signals &= ~(1ULL << sig);
myproc()->saved_sigtf = *tf;
// The handler is free to use %xmm; the code it interrupted had values
// there. Put back by rt_sigreturn.
fxsave(myproc()->sigfpu);
myproc()->in_signal = 1;
tf->rsp = sp;