From e33af8e9021199696e413057b57fb86e750a9de0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20R=C3=B8nne=20Petersen?= <alex@alexrp.com>
Date: Thu, 25 Jul 2024 19:06:38 +0200
Subject: [PATCH] start: Perform the posixCallMainAndExit() call with jalr on
 mips.

It's actually important for the ABI that r25 (t9) contains the address of the
called function, so that this standard prologue sequence works:

    lui $2, %hi(_gp_disp)
    addiu $2, $2, %lo(_gp_disp)
    addu $gp, $2, $t9

(This is a bit similar to the ToC situation on powerpc that was fixed in
7bc78967b400322a0fc5651f37a1b0428c37fb9d.)
---
 lib/std/start.zig | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/lib/std/start.zig b/lib/std/start.zig
index 78845904d6..fcc7fcd100 100644
--- a/lib/std/start.zig
+++ b/lib/std/start.zig
@@ -329,31 +329,43 @@ fn _start() callconv(.Naked) noreturn {
             \\ jsr (%%pc, %%a0)
             ,
             .mips, .mipsel =>
+            \\ move $fp, $0
             \\ bal 1f
             \\ .gpword .
+            \\ .gpword %[posixCallMainAndExit]
             \\ 1:
             \\ lw $gp, 0($ra)
             \\ subu $gp, $ra, $gp
-            \\ move $fp, $0
+            \\ lw $25, 4($ra)
+            \\ addu $25, $25, $gp
             \\ move $ra, $0
             \\ move $a0, $sp
             \\ and $sp, -8
-            \\ j %[posixCallMainAndExit]
+            \\ subu $sp, $sp, 16
+            \\ jalr $25
             ,
             .mips64, .mips64el =>
+            \\ move $fp, $0
+            // This is needed because early MIPS versions don't support misaligned loads. Without
+            // this directive, the hidden `nop` inserted to fill the delay slot after `bal` would
+            // cause the two doublewords to be aligned to 4 bytes instead of 8.
+            \\ .balign 8
             \\ bal 1f
             \\ .gpdword .
+            \\ .gpdword %[posixCallMainAndExit]
             \\ 1:
             // The `gp` register on MIPS serves a similar purpose to `r2` (ToC pointer) on PPC64.
             // We need to set it up in order for dynamically-linked / position-independent code to
             // work.
             \\ ld $gp, 0($ra)
             \\ dsubu $gp, $ra, $gp
-            \\ move $fp, $0
+            \\ ld $25, 8($ra)
+            \\ daddu $25, $25, $gp
             \\ move $ra, $0
             \\ move $a0, $sp
             \\ and $sp, -16
-            \\ j %[posixCallMainAndExit]
+            \\ dsubu $sp, $sp, 16
+            \\ jalr $25
             ,
             .powerpc, .powerpcle =>
             // Set up the initial stack frame, and clear the back chain pointer.