[musl] [PATCH] s390x: manually inline __tls_get_addr in __tls_get_offset

["Alex Rønne Petersen" <alex@alexrp.com>]

Calling __tls_get_addr with brasl is not valid since it's a global symbol; doing
so results in an R_390_PC32DBL relocation error from lld. We could fix this by
marking __tls_get_addr hidden since it is not part of the s390x ABI, or by using
a different instruction. However, given its simplicity, it makes more sense to
just manually inline it into __tls_get_offset for performance.

The patch has been tested by applying to Zig's bundled musl copy and running the
full Zig test suite under qemu-s390x.
---
 src/thread/s390x/__tls_get_offset.s | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/src/thread/s390x/__tls_get_offset.s b/src/thread/s390x/__tls_get_offset.s
index 8ee92de8..405f118b 100644
--- a/src/thread/s390x/__tls_get_offset.s
+++ b/src/thread/s390x/__tls_get_offset.s
@@ -1,17 +1,17 @@
 	.global __tls_get_offset
 	.type __tls_get_offset,%function
 __tls_get_offset:
-	stmg  %r14, %r15, 112(%r15)
-	aghi  %r15, -160
+	ear   %r0, %a0
+	sllg  %r0, %r0, 32
+	ear   %r0, %a1
 
-	la    %r2, 0(%r2, %r12)
-	brasl %r14, __tls_get_addr
+	la    %r1, 0(%r2, %r12)
 
-	ear   %r1, %a0
-	sllg  %r1, %r1, 32
-	ear   %r1, %a1
+	lg    %r3, 0(%r1)
+	sllg  %r4, %r3, 3
+	lg    %r5, 8(%r0)
+	lg    %r2, 0(%r4, %r5)
+	ag    %r2, 8(%r1)
+	sgr   %r2, %r0
 
-	sgr   %r2, %r1
-
-	lmg   %r14, %r15, 272(%r15)
 	br    %r14
-- 
2.43.0