RISC-V TLSDESC works!

I'll make this post more polished.

Patch musl per Re: Draft riscv64 TLSDESC implementation

diff --git c/arch/riscv64/reloc.h w/arch/riscv64/reloc.h
index 1ca13811..7c7c0611 100644
--- c/arch/riscv64/reloc.h
+++ w/arch/riscv64/reloc.h
@@ -17,6 +17,7 @@
 #define REL_DTPMOD      R_RISCV_TLS_DTPMOD64
 #define REL_DTPOFF      R_RISCV_TLS_DTPREL64
 #define REL_TPOFF       R_RISCV_TLS_TPREL64
+#define REL_TLSDESC     R_RISCV_TLSDESC

#define CRTJMP(pc,sp) __asm__ __volatile__( \
        "mv sp, %1 ; jr %0" : : "r"(pc), "r"(sp) : "memory" )
diff --git c/include/elf.h w/include/elf.h
index 72d17c3a..7f342a23 100644
--- c/include/elf.h
+++ w/include/elf.h
@@ -3254,6 +3254,7 @@ enum
 #define R_RISCV_TLS_DTPREL64    9
 #define R_RISCV_TLS_TPREL32     10
 #define R_RISCV_TLS_TPREL64     11
+#define R_RISCV_TLSDESC         12

#define R_RISCV_BRANCH          16
 #define R_RISCV_JAL             17
diff --git c/src/ldso/riscv64/tlsdesc.s w/src/ldso/riscv64/tlsdesc.s
new file mode 100644
index 00000000..56d1ce89
--- /dev/null
+++ w/src/ldso/riscv64/tlsdesc.s
@@ -0,0 +1,33 @@
+.text
+.global __tlsdesc_static
+.hidden __tlsdesc_static
+.type __tlsdesc_static,%function
+__tlsdesc_static:
+       ld a0,8(a0)
+       jr t0
+
+.global __tlsdesc_dynamic
+.hidden __tlsdesc_dynamic
+.type __tlsdesc_dynamic,%function
+__tlsdesc_dynamic:
+       add sp,sp,-16
+       sd t1,(sp)
+       sd t2,8(sp)
+
+       ld t2,-8(tp) # t2=dtv
+
+       ld a0,8(a0)  # a0=&{modidx,off}
+       ld t1,8(a0)  # t1=off
+       ld a0,(a0)   # a0=modidx
+       sll a0,a0,3  # a0=8*modidx
+
+       add a0,a0,t2 # a0=dtv+8*modidx
+       ld a0,(a0)   # a0=dtv[modidx]
+       add a0,a0,t1 # a0=dtv[modidx]+off
+       sub a0,a0,tp # a0=dtv[modidx]+off-tp
+
+       ld t1,(sp)
+       ld t2,8(sp)
+       add sp,sp,16
+       jr t0
+

(mkdir -p out/rv64 && cd out/rv64 && ../../configure --target=riscv64-linux-gnu && make -j 50)

Adjust ~/musl/out/rv64/lib/musl-gcc.specs and update ~/musl/out/rv64/obj/musl-gcc

cat > ~/musl/out/rv64/obj/musl-gcc <<eof
#!/bin/sh
exec "${REALGCC:-riscv64-linux-gnu-gcc}" "$@" -specs ~/musl/out/rv64/lib/musl-gcc.specs
eof

Prepare a runtime test mentioned at the end of https://maskray.me/blog/2021-02-14-all-about-thread-local-storage

cat > ./a.c <<eof
#include <assert.h>
int foo();
int bar();
int main() {
  assert(foo() == 2);
  assert(foo() == 4);
  assert(bar() == 2);
  assert(bar() == 4);
}
eof

cat > ./b.c <<eof
#include <stdio.h>
__thread int tls0;
extern __thread int tls1;
int foo() { return ++tls0 + ++tls1; }
static __thread int tls2, tls3;
int bar() { return ++tls2 + ++tls3; }
eof

echo '__thread int tls1;' > ./c.c

sed 's/        /\t/' > ./Makefile <<'eof'
.MAKE.MODE = meta curDirOk=true

CC := ~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld
LDFLAGS := -Wl,-rpath=.

all: a0 a1 a2

run: all
        ./a0 && ./a1 && ./a2

b.o: bb.s
        /tmp/Rel/bin/clang --target=riscv64-linux -c bb.s -o $@
c.so: c.o; ${LINK.c} -shared $> -o $@
bc.so: b.o c.o; ${LINK.c} -shared $> -o $@
b.so: b.o c.so; ${LINK.c} -shared $> -o $@

a0: a.o b.o c.o; ${LINK.c} $> -o $@
a1: a.o b.so; ${LINK.c} $> -o $@
a2: a.o bc.so; ${LINK.c} $> -o $@
eof

Compile b.c to bb.s. Replace general-dynamic code sequences (e.g. la.tls.gd a0,tls0; call __tls_get_addr@plt) with TLSDESC, e.g.

.Ltlsdesc_hi0:
  auipc a0, %tlsdesc_hi(tls0)
  ld  a1, %tlsdesc_load_lo(.Ltlsdesc_hi0)(a0)
  addi  a0, a0, %tlsdesc_add_lo(.Ltlsdesc_hi0)
  jalr  t0, 0(a1), %tlsdesc_call(.Ltlsdesc_hi0)
  add   a0, a0, tp

Apply LLVM CodeGen/assembly and lld patch (https://github.com/llvm/llvm-project/pull/79099) to llvm-project. Build clang and lld. Create an alias bin/ld.lld to be used with -Bbin -fuse-ld=lld.

bmake run => succeeded!

% bmake run
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -c a.c
/tmp/Rel/bin/clang --target=riscv64-linux -c bb.s -o b.o
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -c c.c
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. a.o b.o c.o -o a0
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. -shared c.o -o c.so
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. -shared b.o c.so -o b.so
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. a.o b.so -o a1
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. -shared b.o c.o -o bc.so
~/musl/out/rv64/obj/musl-gcc -O1 -g -fpic -Bbin -fuse-ld=lld -g  -Wl,-rpath=. a.o bc.so -o a2
./a0 && ./a1 && ./a2