sx/examples/1808-concurrency-fiber-switch-stress.sx

// Stream B1 (fibers) B1.3a-2 — the context-switch STRESS GATE (design §10.7):
// explicitly scribble EVERY callee-saved register with a sentinel, switch, and
// verify every one survived. This is the correctness gate the run/snapshot
// tests can't be — a switch that drops a register "happens to print right".
//
// `swap_context` here saves the COMPLETE AAPCS64 callee-saved set: the integer
// regs x19-x28 + x29(fp) + x30(lr) + sp, AND the FP regs d8-d15. Per AAPCS64
// §6.1.2 only the LOW 64 bits of v8-v15 are callee-saved, so `d8-d15` is exactly
// sufficient (q8-q15 is not required). x18 is the Apple platform register —
// reserved, never touched. (1807 is the foundational GP-only switch; this is the
// complete one + the explicit gate.)
//
// The gate is a 2-fiber MUTUAL scribble: A loads sentinels base_A+1.. into every
// callee-saved reg and yields; while A is suspended, B loads its OWN distinct
// sentinels into the same physical registers; when A resumes it checks every reg
// still holds base_A — which is only possible if `swap_context` saved+restored
// it. (A single fiber yielding to an idle peer would NOT exercise preservation —
// the peer must clobber the registers. Validated adversarially: dropping the
// d8-d15 save/restore makes this report 8 mismatches; dropping x27/x28 reports 2.)
//
// Honest scope (what a register-sentinel gate does NOT cover, all spec-correct
// for a call-boundary swap but worth stating): NZCV flags, FPSR, FPCR (rounding
// mode — thread-global, bleeds across fibers if changed), and TPIDR_EL0/TLS
// (errno, allocator thread-caches — shared by same-thread fibers) are not
// swapped. fp=0 bootstrap means unwinders/signal handlers can't walk past a
// fiber's trampoline (no CFI for the swap). These matter at the N×M:1 / signals
// stages, not for the single-thread switch this gate proves.
//
// aarch64-pinned (per-arch asm + 21-slot save area); runs end-to-end here,
// ir-only on a mismatch. x86_64 sibling + mmap guard-page stacks are B1.3b.
#import "modules/std.sx";

// 21 slots: [0..9]=x19..x28 [10]=fp [11]=lr [12]=sp [13..20]=d8..d15.
FiberCtx :: struct { regs: [21]u64; }

Fiber :: struct {
    ctx: FiberCtx;
    peer: *FiberCtx;   // scribble_verify yields here — the clobberer
    next: *FiberCtx;   // where to switch after verifying
    base: u64;
    mismatches: i64;
}

// The complete switch: save callee-saved (x19-x28, fp, lr, sp, d8-d15) into
// *from, load from *to, ret onto to's stack. x0=from, x1=to (read straight from
// the ABI registers — a naked fn has no frame). `export`ed so scribble_verify
// can reach it by symbol with `bl`.
swap_context :: (from: *FiberCtx, to: *FiberCtx) abi(.naked) export "swap_context" {
    asm volatile {
        #string ASM
        stp x19, x20, [x0, #0]
        stp x21, x22, [x0, #16]
        stp x23, x24, [x0, #32]
        stp x25, x26, [x0, #48]
        stp x27, x28, [x0, #64]
        stp x29, x30, [x0, #80]
        mov x9, sp
        str x9, [x0, #96]
        stp d8, d9,   [x0, #104]
        stp d10, d11, [x0, #120]
        stp d12, d13, [x0, #136]
        stp d14, d15, [x0, #152]
        ldp x19, x20, [x1, #0]
        ldp x21, x22, [x1, #16]
        ldp x23, x24, [x1, #32]
        ldp x25, x26, [x1, #48]
        ldp x27, x28, [x1, #64]
        ldp x29, x30, [x1, #80]
        ldr x9, [x1, #96]
        mov sp, x9
        ldp d8, d9,   [x1, #104]
        ldp d10, d11, [x1, #120]
        ldp d12, d13, [x1, #136]
        ldp d14, d15, [x1, #152]
        ret
ASM
    };
}

// Load sentinel base+1..+10 into x19-x28 and base+11..+18 into d8-d15, yield to
// `peer`, and on resume count the registers that did NOT survive. Naked, so it
// honors its caller's ABI by hand: a 176-byte frame saves the CALLER's
// callee-saved (which it clobbers) + base (x2 is not preserved across the swap);
// after the swap it reloads base, compares every reg, restores the caller's
// regs, and returns the mismatch count in x0. The original return address is
// saved (frame+88) before the `bl` and reloaded after — the swap round-trips
// sp+lr, so execution resumes right after the `bl` on the same frame.
scribble_verify :: (self_ctx: *FiberCtx, peer: *FiberCtx, base: u64) -> i64 abi(.naked) export "scribble_verify" {
    asm volatile {
        #string SV
        sub sp, sp, #176
        stp x19, x20, [sp, #0]
        stp x21, x22, [sp, #16]
        stp x23, x24, [sp, #32]
        stp x25, x26, [sp, #48]
        stp x27, x28, [sp, #64]
        stp x29, x30, [sp, #80]
        stp d8, d9,   [sp, #96]
        stp d10, d11, [sp, #112]
        stp d12, d13, [sp, #128]
        stp d14, d15, [sp, #144]
        str x2, [sp, #160]
        add x19, x2, #1
        add x20, x2, #2
        add x21, x2, #3
        add x22, x2, #4
        add x23, x2, #5
        add x24, x2, #6
        add x25, x2, #7
        add x26, x2, #8
        add x27, x2, #9
        add x28, x2, #10
        add x9, x2, #11
        fmov d8, x9
        add x9, x2, #12
        fmov d9, x9
        add x9, x2, #13
        fmov d10, x9
        add x9, x2, #14
        fmov d11, x9
        add x9, x2, #15
        fmov d12, x9
        add x9, x2, #16
        fmov d13, x9
        add x9, x2, #17
        fmov d14, x9
        add x9, x2, #18
        fmov d15, x9
        bl _swap_context
        ldr x2, [sp, #160]
        mov x10, #0
        add x9, x2, #1
        cmp x19, x9
        cinc x10, x10, ne
        add x9, x2, #2
        cmp x20, x9
        cinc x10, x10, ne
        add x9, x2, #3
        cmp x21, x9
        cinc x10, x10, ne
        add x9, x2, #4
        cmp x22, x9
        cinc x10, x10, ne
        add x9, x2, #5
        cmp x23, x9
        cinc x10, x10, ne
        add x9, x2, #6
        cmp x24, x9
        cinc x10, x10, ne
        add x9, x2, #7
        cmp x25, x9
        cinc x10, x10, ne
        add x9, x2, #8
        cmp x26, x9
        cinc x10, x10, ne
        add x9, x2, #9
        cmp x27, x9
        cinc x10, x10, ne
        add x9, x2, #10
        cmp x28, x9
        cinc x10, x10, ne
        add x9, x2, #11
        fmov x11, d8
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #12
        fmov x11, d9
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #13
        fmov x11, d10
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #14
        fmov x11, d11
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #15
        fmov x11, d12
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #16
        fmov x11, d13
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #17
        fmov x11, d14
        cmp x11, x9
        cinc x10, x10, ne
        add x9, x2, #18
        fmov x11, d15
        cmp x11, x9
        cinc x10, x10, ne
        ldp x19, x20, [sp, #0]
        ldp x21, x22, [sp, #16]
        ldp x23, x24, [sp, #32]
        ldp x25, x26, [sp, #48]
        ldp x27, x28, [sp, #64]
        ldp x29, x30, [sp, #80]
        ldp d8, d9,   [sp, #96]
        ldp d10, d11, [sp, #112]
        ldp d12, d13, [sp, #128]
        ldp d14, d15, [sp, #144]
        mov x0, x10
        add sp, sp, #176
        ret
SV
    };
}

asm {
    #string T
.global _fib_tramp
_fib_tramp:
    mov x0, x19
    bl _fib_body
    brk #0
T,
};

fib_tramp :: () extern;

fib_body :: (self: *Fiber) export "fib_body" {
    self.mismatches = scribble_verify(@self.ctx, self.peer, self.base);
    swap_context(@self.ctx, self.next);
}

STACK :: 131072;

boot :: (f: *Fiber) {
    base : *void = context.allocator.alloc_bytes(STACK);
    top : u64 = (xx base) + STACK;
    top = top - (top % 16);
    f.ctx.regs[0]  = xx f;            // x19 = self
    f.ctx.regs[10] = 0;              // fp
    f.ctx.regs[11] = xx fib_tramp;   // lr → trampoline
    f.ctx.regs[12] = top;            // sp
    // Zero the FP save slots so the first switch-to loads 0 (not garbage) into
    // d8-d15 — removes the first-entry foot-gun (adversarial-review note).
    i := 13;
    while i < 21 { f.ctx.regs[i] = 0; i = i + 1; }
    f.mismatches = -1;
}

main :: () -> i64 {
    main_ctx : FiberCtx = ---;
    a : Fiber = ---;  a.base = 0x5000;
    b : Fiber = ---;  b.base = 0x6000;
    a.peer = @b.ctx;  a.next = @b.ctx;     // A yields to B, then hands B the baton
    b.peer = @a.ctx;  b.next = @main_ctx;  // B yields to A, then returns to main
    boot(@a);  boot(@b);
    swap_context(@main_ctx, @a.ctx);
    print("A mismatches: {}\n", a.mismatches);   // 0 — every callee-saved survived
    print("B mismatches: {}\n", b.mismatches);   // 0
    return 0;
}