Save vector/float registers on ARM too.

crates/fiber/src/arch/aarch64.S

@@ -26,6 +26,10 @@ FUNCTION(wasmtime_fiber_switch):
  stp x24, x23, [sp, -16]!
  stp x26, x25, [sp, -16]!
  stp x28, x27, [sp, -16]!
+ stp d9, d8, [sp, -16]!
+ stp d11, d10, [sp, -16]!
+ stp d13, d12, [sp, -16]!
+ stp d15, d14, [sp, -16]!
 
  // Load our previously saved stack pointer to resume to, and save off our
  // current stack pointer on where to come back to eventually.
@@ -36,6 +40,10 @@ FUNCTION(wasmtime_fiber_switch):
  // Switch to the new stack and restore all our callee-saved registers after
  // the switch and return to our new stack.
  mov sp, x8
+ ldp d15, d14, [sp], 16
+ ldp d13, d12, [sp], 16
+ ldp d11, d10, [sp], 16
+ ldp d9, d8, [sp], 16
  ldp x28, x27, [sp], 16
  ldp x26, x25, [sp], 16
  ldp x24, x23, [sp], 16
@@ -58,9 +66,9 @@ FUNCTION(wasmtime_fiber_init):
  stp x0, x8, [x0, -0x28] // x0 => x19, x8 => lr
  stp x2, x1, [x0, -0x38] // x1 => x20, x2 => x21
 
- // `wasmtime_fiber_switch` has an 0x60 byte stack, and we add 0x10 more for
+ // `wasmtime_fiber_switch` has an 0xa0 byte stack, and we add 0x10 more for
  // the original reserved 16 bytes.
- add x8, x0, -0x70
+ add x8, x0, -0xb0
  str x8, [x0, -0x10]
  ret
 SIZE(wasmtime_fiber_init)
@@ -73,11 +81,11 @@ FUNCTION(wasmtime_fiber_start):
  // See the x86_64 file for more commentary on what these CFI directives are
  // doing. Like over there note that the relative offsets to registers here
  // match the frame layout in `wasmtime_fiber_switch`.
- .cfi_escape 0x0f, /* DW_CFA_def_cfa_expression */ \
- 4,  /* the byte length of this expression */ \
- 0x6f, /* DW_OP_reg31(%sp) */ \
- 0x06, /* DW_OP_deref */ \
- 0x23, 0x60 /* DW_OP_plus_uconst 0x60 */
+ .cfi_escape 0x0f,  /* DW_CFA_def_cfa_expression */ \
+ 5,  /* the byte length of this expression */ \
+ 0x6f,  /* DW_OP_reg31(%sp) */ \
+ 0x06,  /* DW_OP_deref */ \
+ 0x23, 0xa0, 0x1 /* DW_OP_plus_uconst 0xa0 */
 
  .cfi_rel_offset lr, -0x10
  .cfi_rel_offset x19, -0x18

crates/fiber/src/arch/x86_64.S

@@ -134,10 +134,10 @@ FUNCTION(wasmtime_fiber_start):
  // the return address of the caller's `call` instruction. Hence we offset
  // another 0x38 bytes.
  .cfi_escape 0x0f, /* DW_CFA_def_cfa_expression */ \
- 5, /* the byte length of this expression */ \
- 0x77, 0x18, /* DW_OP_breg7 (%rsp) + 0x18 */ \
- 0x06, /* DW_OP_deref */ \
- 0x23, 0x38 /* DW_OP_plus_uconst 0x38 */
+ 5, /* the byte length of this expression */ \
+ 0x77, 0x18, /* DW_OP_breg7 (%rsp) + 0x18 */ \
+ 0x06, /* DW_OP_deref */ \
+ 0x23, 0x38 /* DW_OP_plus_uconst 0x38 */
 
  // And now after we've indicated where our CFA is for our parent function,
  // we can define that where all of the saved registers are located. This