overhaul sh atomics for new atomics framework, add j-core cas.l backend

sh needs runtime-selected atomic backends since there are a number of
supported models that use non-forwards-compatible (non-smp-compatible)
atomic mechanisms. previously, the code paths for this were highly
inefficient since they involved C function calls with multiple
branches in the callee and heavy spills in the caller. the new code
performs calls the runtime-selected asm fragment from inline asm with
extremely minimal clobbers, rather than using a function call.

for the sh4a case where the atomic mechanism is known and there is no
forward-compatibility issue, the movli.l and movco.l instructions are
provided as a_ll and a_sc, allowing the new shared atomic.h to
generate efficient inline versions of all the basic atomic operations
without needing a cas loop.

1 files changed, 40 insertions, 0 deletions

diff --git a/src/thread/sh/__set_thread_area.c b/src/thread/sh/__set_thread_area.c
new file mode 100644
index 00000000..9c47f78d
--- /dev/null
+++ b/src/thread/sh/__set_thread_area.c
@@ -0,0 +1,40 @@
+#include "pthread_impl.h"
+#include "libc.h"
+#include <elf.h>
+
+/* Also perform sh-specific init */
+
+#define CPU_HAS_LLSC 0x0040
+#define CPU_HAS_CAS_L 0x0400
+
+__attribute__((__visibility__("hidden")))
+extern const char __sh_cas_gusa[], __sh_cas_llsc[], __sh_cas_imask[], __sh_cas_cas_l[];
+
+__attribute__((__visibility__("hidden")))
+const void *__sh_cas_ptr;
+
+__attribute__((__visibility__("hidden")))
+unsigned __sh_nommu;
+
+int __set_thread_area(void *p)
+{
+	size_t *aux;
+	__asm__ __volatile__ ( "ldc %0, gbr" : : "r"(p) : "memory" );
+#ifndef __SH4A__
+	__sh_cas_ptr = __sh_cas_gusa;
+#if !defined(__SH3__) && !defined(__SH4__)
+	for (aux=libc.auxv; *aux; aux+=2) {
+		if (*aux != AT_PLATFORM) continue;
+		const char *s = (void *)aux[1];
+		if (s[0]!='s' || s[1]!='h' || s[2]!='2' || s[3]-'0'<10u) break;
+		__sh_cas_ptr = __sh_cas_imask;
+		__sh_nommu = 1;
+	}
+#endif
+	if (__hwcap & CPU_HAS_CAS_L)
+		__sh_cas_ptr = __sh_cas_cas_l;
+	else if (__hwcap & CPU_HAS_LLSC)
+		__sh_cas_ptr = __sh_cas_llsc;
+#endif
+	return 0;
+}