RFR: JDK-8274795: AArch64: avoid spilling and restoring r18 in macro assembler [v2]

[Bernhard Urban-Forster]

On Wed, 6 Oct 2021 09:26:35 GMT, Andrew Haley <aph at openjdk.org> wrote:

> Sorry, stupid mistake: the pop is done in reverse, of course!

hmm, I think it's fine. Checkout the full listing:


 0x0000000130009f80:   b.ne    0x000000013000a018  // b.any
  0x0000000130009f84:   stp x0, x1, [sp, #-256]!
  0x0000000130009f88:   stp x2, x3, [sp, #16]
  0x0000000130009f8c:   stp x4, x5, [sp, #32]
  0x0000000130009f90:   stp x6, x7, [sp, #48]
  0x0000000130009f94:   stp x8, x9, [sp, #64]
  0x0000000130009f98:   stp x10, x11, [sp, #80]
  0x0000000130009f9c:   stp x12, x13, [sp, #96]
  0x0000000130009fa0:   stp x14, x15, [sp, #112]
  0x0000000130009fa4:   stp x16, x17, [sp, #128]
  0x0000000130009fa8:   stp x18, x19, [sp, #144]
  0x0000000130009fac:   stp x20, x21, [sp, #160]
  0x0000000130009fb0:   stp x22, x23, [sp, #176]
  0x0000000130009fb4:   stp x24, x25, [sp, #192]
  0x0000000130009fb8:   stp x26, x27, [sp, #208]
  0x0000000130009fbc:   stp x28, x29, [sp, #224]
  0x0000000130009fc0:   stp x30, xzr, [sp, #240]
  0x0000000130009fc4:   mov x0, x28
 ;; 0x10564AC0C
  0x0000000130009fc8:   mov x9, #0xac0c                 // #44044
  0x0000000130009fcc:   movk    x9, #0x564, lsl #16
  0x0000000130009fd0:   movk    x9, #0x1, lsl #32
  0x0000000130009fd4:   blr x9
  0x0000000130009fd8:   ldp x2, x3, [sp, #16]
  0x0000000130009fdc:   ldp x4, x5, [sp, #32]
  0x0000000130009fe0:   ldp x6, x7, [sp, #48]
  0x0000000130009fe4:   ldp x8, x9, [sp, #64]
  0x0000000130009fe8:   ldp x10, x11, [sp, #80]
  0x0000000130009fec:   ldp x12, x13, [sp, #96]
  0x0000000130009ff0:   ldp x14, x15, [sp, #112]
  0x0000000130009ff4:   ldp x16, x17, [sp, #128]
  0x0000000130009ff8:   ldp x0, x1, [sp], #144
  0x0000000130009ffc:   ldp xzr, x19, [sp], #16
  0x000000013000a000:   ldp x22, x23, [sp, #16]
  0x000000013000a004:   ldp x24, x25, [sp, #32]
  0x000000013000a008:   ldp x26, x27, [sp, #48]
  0x000000013000a00c:   ldp x28, x29, [sp, #64]
  0x000000013000a010:   ldp x30, xzr, [sp, #80]
  0x000000013000a014:   ldp x20, x21, [sp], #96
  0x000000013000a018:   ldur    x12, [x29, #-24]
  0x000000013000a01c:   ldr x22, [x12, #16]
  0x000000013000a020:   add x22, x22, #0x30
  0x000000013000a024:   ldr x8, [x28, #8]


In terms of testing, it seems hard to trigger, so I forced the code path via:

diff --git a/src/hotspot/cpu/aarch64/templateInterpreterGenerator_aarch64.cpp b/src/hotspot/cpu/aarch64/templateInterpreterGenerator_aarch64.cpp
index d069345b9c0..046c325faa7 100644
--- a/src/hotspot/cpu/aarch64/templateInterpreterGenerator_aarch64.cpp
+++ b/src/hotspot/cpu/aarch64/templateInterpreterGenerator_aarch64.cpp
@@ -1392,11 +1392,14 @@ address TemplateInterpreterGenerator::generate_native_entry(bool synchronized) {

   {
     Label no_reguard;
+    Label skip_check;
+    __ b(skip_check);
     __ lea(rscratch1, Address(rthread, in_bytes(JavaThread::stack_guard_state_offset())));
     __ ldrw(rscratch1, Address(rscratch1));
     __ cmp(rscratch1, (u1)StackOverflow::stack_guard_yellow_reserved_disabled);
     __ br(Assembler::NE, no_reguard);

+    __ bind(skip_check);
     __ push(RegSet::range(r0, r30), sp);
     __ mov(c_rarg0, rthread);
     __ mov(rscratch2, CAST_FROM_FN_PTR(address, SharedRuntime::reguard_yellow_pages));


which crashes with your most recent suggestion btw, but it's fine with what's in this PR right now.

Any better suggestion on how to test it?

-------------

PR: https://git.openjdk.java.net/jdk/pull/5828