6 files changed, 76 insertions, 18 deletions
diff --git a/src/ldso/dl_iterate_phdr.c b/src/ldso/dl_iterate_phdr.c
index 86c87ef8..9546dd36 100644
--- a/src/ldso/dl_iterate_phdr.c
+++ b/src/ldso/dl_iterate_phdr.c
@@ -1,5 +1,6 @@
 #include <elf.h>
 #include <link.h>
+#include "pthread_impl.h"
 #include "libc.h"
 
 #define AUX_CNT 38
@@ -35,7 +36,7 @@ static int static_dl_iterate_phdr(int(*callback)(struct dl_phdr_info *info, size
 	info.dlpi_subs  = 0;
 	if (tls_phdr) {
 		info.dlpi_tls_modid = 1;
-		info.dlpi_tls_data = (void *)(base + tls_phdr->p_vaddr);
+		info.dlpi_tls_data = __tls_get_addr((tls_mod_off_t[]){1,0});
 	} else {
 		info.dlpi_tls_modid = 0;
 		info.dlpi_tls_data = 0;
diff --git a/src/ldso/dlerror.c b/src/ldso/dlerror.c
index 3fcc7779..dae0f3a9 100644
--- a/src/ldso/dlerror.c
+++ b/src/ldso/dlerror.c
@@ -3,7 +3,12 @@
 #include <stdarg.h>
 #include "pthread_impl.h"
 #include "dynlink.h"
-#include "lock.h"
+#include "atomic.h"
+
+#define malloc __libc_malloc
+#define calloc __libc_calloc
+#define realloc __libc_realloc
+#define free __libc_free
 
 char *dlerror()
 {
@@ -17,30 +22,37 @@ char *dlerror()
 		return s;
 }
 
-static volatile int freebuf_queue_lock[1];
-static void **freebuf_queue;
+/* Atomic singly-linked list, used to store list of thread-local dlerror
+ * buffers for deferred free. They cannot be freed at thread exit time
+ * because, by the time it's known they can be freed, the exiting thread
+ * is in a highly restrictive context where it cannot call (even the
+ * libc-internal) free. It also can't take locks; thus the atomic list. */
+
+static void *volatile freebuf_queue;
 
 void __dl_thread_cleanup(void)
 {
 	pthread_t self = __pthread_self();
-	if (self->dlerror_buf && self->dlerror_buf != (void *)-1) {
-		LOCK(freebuf_queue_lock);
-		void **p = (void **)self->dlerror_buf;
-		*p = freebuf_queue;
-		freebuf_queue = p;
-		UNLOCK(freebuf_queue_lock);
-	}
+	if (!self->dlerror_buf || self->dlerror_buf == (void *)-1)
+		return;
+	void *h;
+	do {
+		h = freebuf_queue;
+		*(void **)self->dlerror_buf = h;
+	} while (a_cas_p(&freebuf_queue, h, self->dlerror_buf) != h);
 }
 
 hidden void __dl_vseterr(const char *fmt, va_list ap)
 {
-	LOCK(freebuf_queue_lock);
-	while (freebuf_queue) {
-		void **p = freebuf_queue;
-		freebuf_queue = *p;
-		free(p);
+	void **q;
+	do q = freebuf_queue;
+	while (q && a_cas_p(&freebuf_queue, q, 0) != q);
+
+	while (q) {
+		void **p = *q;
+		free(q);
+		q = p;
 	}
-	UNLOCK(freebuf_queue_lock);
 
 	va_list ap2;
 	va_copy(ap2, ap);
diff --git a/src/ldso/loongarch64/dlsym.s b/src/ldso/loongarch64/dlsym.s
new file mode 100644
index 00000000..26fabcdb
--- /dev/null
+++ b/src/ldso/loongarch64/dlsym.s
@@ -0,0 +1,7 @@
+.global dlsym
+.hidden __dlsym
+.type   dlsym,@function
+dlsym:
+	move      $a2, $ra
+	la.global $t0, __dlsym
+	jr        $t0
diff --git a/src/ldso/riscv32/dlsym.s b/src/ldso/riscv32/dlsym.s
new file mode 100644
index 00000000..2bafd72d
--- /dev/null
+++ b/src/ldso/riscv32/dlsym.s
@@ -0,0 +1,6 @@
+.global dlsym
+.hidden __dlsym
+.type dlsym, %function
+dlsym:
+	mv a2, ra
+	tail __dlsym
diff --git a/src/ldso/riscv64/tlsdesc.s b/src/ldso/riscv64/tlsdesc.s
new file mode 100644
index 00000000..bef8b322
--- /dev/null
+++ b/src/ldso/riscv64/tlsdesc.s
@@ -0,0 +1,32 @@
+.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
diff --git a/src/ldso/sh/dlsym.s b/src/ldso/sh/dlsym.s
index 11a6fff5..34f3c35c 100644
--- a/src/ldso/sh/dlsym.s
+++ b/src/ldso/sh/dlsym.s
@@ -5,7 +5,7 @@
 dlsym:
 	mov.l L1, r0
 1:	braf  r0
-	 mov.l @r15, r6
+	 sts pr, r6
 
 .align 2
 L1:	.long __dlsym@PLT-(1b+4-.)