py/nlr: Factor out common NLR code to generic functions.

Each NLR implementation (Thumb, x86, x64, xtensa, setjmp) duplicates a lot
of the NLR code, specifically that dealing with pushing and popping the NLR
pointer to maintain the linked-list of NLR buffers.  This patch factors all
of that code out of the specific implementations into generic functions in
nlr.c.  This eliminates duplicated code.

The factoring also allows to make the machine-specific NLR code pure
assembler code, thus allowing nlrthumb.c to use naked function attributes
in the correct way (naked functions can only have basic inline assembler
code in them).

There is a small overhead introduced (typically 1 machine instruction)
because now the generic nlr_jump() must call nlr_jump_tail() rather than
them being one combined function.

1 files changed, 13 insertions, 50 deletions

diff --git a/py/nlrx86.c b/py/nlrx86.c
index 3a27460eb..cc37f72af 100644
--- a/py/nlrx86.c
+++ b/py/nlrx86.c
@@ -26,25 +26,13 @@
 
 #include "py/mpstate.h"
 
-#if !MICROPY_NLR_SETJMP && defined(__i386__)
+#if MICROPY_NLR_X86
 
 #undef nlr_push
 
 // For reference, x86 callee save regs are:
 //  ebx, esi, edi, ebp, esp, eip
 
-#if defined(_WIN32) || defined(__CYGWIN__)
-#define NLR_OS_WINDOWS 1
-#else
-#define NLR_OS_WINDOWS 0
-#endif
-
-#if NLR_OS_WINDOWS
-unsigned int nlr_push_tail(nlr_buf_t *nlr) asm("nlr_push_tail");
-#else
-__attribute__((used)) unsigned int nlr_push_tail(nlr_buf_t *nlr);
-#endif
-
 unsigned int nlr_push(nlr_buf_t *nlr) {
     (void)nlr;
 
@@ -70,48 +58,23 @@ unsigned int nlr_push(nlr_buf_t *nlr) {
     return 0; // needed to silence compiler warning
 }
 
-__attribute__((used)) unsigned int nlr_push_tail(nlr_buf_t *nlr) {
-    nlr_buf_t **top = &MP_STATE_THREAD(nlr_top);
-    nlr->prev = *top;
-    MP_NLR_SAVE_PYSTACK(nlr);
-    *top = nlr;
-    return 0; // normal return
-}
-
-void nlr_pop(void) {
-    nlr_buf_t **top = &MP_STATE_THREAD(nlr_top);
-    *top = (*top)->prev;
-}
-
-NORETURN void nlr_jump(void *val) {
-    nlr_buf_t **top_ptr = &MP_STATE_THREAD(nlr_top);
-    nlr_buf_t *top = *top_ptr;
-    if (top == NULL) {
-        nlr_jump_fail(val);
-    }
-
-    top->ret_val = val;
-    MP_NLR_RESTORE_PYSTACK(top);
-    *top_ptr = top->prev;
+NORETURN void nlr_jump_tail(nlr_buf_t *top) {
+    (void)top;
 
     __asm volatile (
-    "mov    %0, %%edx           \n" // %edx points to nlr_buf
-    "mov    28(%%edx), %%esi    \n" // load saved %esi
-    "mov    24(%%edx), %%edi    \n" // load saved %edi
-    "mov    20(%%edx), %%ebx    \n" // load saved %ebx
-    "mov    16(%%edx), %%esp    \n" // load saved %esp
-    "mov    12(%%edx), %%ebp    \n" // load saved %ebp
-    "mov    8(%%edx), %%eax     \n" // load saved %eip
-    "mov    %%eax, (%%esp)      \n" // store saved %eip to stack
-    "xor    %%eax, %%eax        \n" // clear return register
-    "inc    %%al                \n" // increase to make 1, non-local return
+    "mov    28(%edx), %esi      \n" // load saved %esi
+    "mov    24(%edx), %edi      \n" // load saved %edi
+    "mov    20(%edx), %ebx      \n" // load saved %ebx
+    "mov    16(%edx), %esp      \n" // load saved %esp
+    "mov    12(%edx), %ebp      \n" // load saved %ebp
+    "mov    8(%edx), %eax       \n" // load saved %eip
+    "mov    %eax, (%esp)        \n" // store saved %eip to stack
+    "xor    %eax, %eax          \n" // clear return register
+    "inc    %al                 \n" // increase to make 1, non-local return
     "ret                        \n" // return
-    :                               // output operands
-    : "r"(top)                      // input operands
-    :                               // clobbered registers
     );
 
     for (;;); // needed to silence compiler warning
 }
 
-#endif // !MICROPY_NLR_SETJMP && defined(__i386__)
+#endif // MICROPY_NLR_X86