Merge pull request #153 from afxgroup/profile

Fixed profiling code

GNUmakefile.os4

@@ -63,7 +63,7 @@ WARNINGS := \
 	-Wundef -Wmissing-declarations -Wunused -Wwrite-strings -Wno-unused-value -Wno-comment -Wno-missing-braces \
 	-Wno-deprecated-declarations -Wno-sign-compare -Wno-unused-variable -Wno-parentheses -Wno-missing-prototypes \
 	-Wstrict-aliasing -Wno-shadow -Wno-discarded-qualifiers -Wno-unused-function -Wno-unused-parameter -Wno-strict-aliasing \
-    -Wno-type-limits -Wno-cast-function-type -Werror # -Wbad-function-cast -Wconversion -Wformat
+    -Wno-type-limits -Wno-cast-function-type -Wno-frame-address -Werror # -Wbad-function-cast -Wconversion -Wformat
 
 PIC		   := -fPIC -DPIC
 INCLUDES   := -I$(LIB_DIR)/include \
@@ -149,7 +149,6 @@ include libc.gmk
 include libm.gmk
 include libamiga.gmk
 include libdebug.gmk
-include libprofile.gmk
 include libpthread.gmk
 include libcrypt.gmk
 include librt.gmk
@@ -200,13 +199,11 @@ clean:
 # Update the version numbers bound to the individual libraries
 version:
 	$(COPY) c.lib_rev.rev amiga/amiga.lib_rev.rev
-	$(COPY) c.lib_rev.rev profile/profile.lib_rev.rev
 	$(COPY) c.lib_rev.rev math/m.lib_rev.rev
 	$(COPY) c.lib_rev.rev math/crypt.lib_rev.rev
 	$(COPY) c.lib_rev.rev math/pthread.lib_rev.rev
 	bumprev amiga.lib
 	bumprev c.lib
-	bumprev profile.lib
 	bumprev m.lib
 	bumprev crypt.lib
 	bumprev pthread.lib

README.md

@@ -1,4 +1,4 @@
- C runtime library for AmigaOS4
+ runtime library for AmigaOS4
 
 [![Build Status](https://travis-ci.com/afxgroup/clib2.svg?branch=master)](https://travis-ci.org/afxgroup/clib2)
 [![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)

libc.gmk

@@ -954,6 +954,10 @@ C_LIBRARY := \
 
 C_LIB := \
 	c.lib_rev.o \
+	profile/_mcount.o \
+	profile/profil.o \
+	profile/gmon.o \
+	profile/mcount.o \
 	shared_library/stubs.o \
 	unistd/getopt.o \
 	unistd/getopt_long.o
@@ -986,6 +990,11 @@ $(OUT_SHARED)/%.o : $(LIB_DIR)/%.c
 	$(VERBOSE)$(COMPILE_SHARED)
 endif
 
+$(OUT_STATIC)/profile/%.o : $(LIB_DIR)/profile/%.S
+	$(VERBOSE)$(COMPILE_REG)
+$(OUT_SHARED)/profile/%.o : $(LIB_DIR)/profile/%.S
+	$(VERBOSE)$(COMPILE_REG)
+
 $(OUTPUT_LIB)/libc.a : $(SOURCES_STATIC)
 	$(VERBOSE)@$(MAKELIB)
 $(OUTPUT_LIB)/libc.so : $(SOURCES_SHARED)

library/cpu/generic/bcopy.S

@@ -66,7 +66,7 @@
 
 // Main entry points.
 
-.align 	5
+    .align 	5
     .global bcopy_g3
 
 bcopy_g3:							// void bcopy(const void *src, void *dst, size_t len)

library/profile/_mcount.c

@@ -1,22 +1,23 @@
 /*
- * $Id: profile__mcount.c,v 1.0 2022-08-06 10:36:26 clib4devs Exp $
+ * $Id: profile__mcount.c,v 1.1 2023-10-20 10:36:26 clib4devs Exp $
 */
 
-#include "profile_gmon.h"
 #include <exec/exec.h>
 #include <proto/exec.h>
 #include <stddef.h>
+#include <stdio.h>
 
+#include "gmon.h"
 
 void __mcount(uint32 frompc, uint32 selfpc);
 
 void
 __mcount(uint32 frompc, uint32 selfpc) {
-    uint16 *frompcindex;
-    struct tostruct *top, *prevtop;
-    struct gmonparam *p;
-
-    int32 toindex;
+    register ARCINDEX *frompcindex;
+    register struct tostruct *top, *prevtop;
+    register struct gmonparam *p;
+    register ARCINDEX toindex;
+    int i;
 
     p = &_gmonparam;
 
@@ -34,43 +35,59 @@ __mcount(uint32 frompc, uint32 selfpc) {
     if (frompc > p->textsize)
         goto done;
 
-#if (HASHFRACTION & (HASHFRACTION - 1)) == 0
-    if (p->hashfraction == HASHFRACTION) {
-        frompcindex = &p->froms[(size_t)(frompc / (HASHFRACTION *
-                                                   sizeof(*p->froms)))];
-    } else
-#endif
-    {
-        frompcindex = &p->froms[(size_t)(frompc / (p->hashfraction *
-                                                   sizeof(*p->froms)))];
+    /* The following test used to be
+		if (p->log_hashfraction >= 0)
+	   But we can simplify this if we assume the profiling data
+	   is always initialized by the functions in gmon.c.  But
+	   then it is possible to avoid a runtime check and use the
+	   same `if' as in gmon.c.  So keep these tests in sync.
+    */
+    if ((HASHFRACTION & (HASHFRACTION - 1)) == 0) {
+        /* avoid integer divide if possible: */
+        i = frompc >> p->log_hashfraction;
+    } else {
+        i = frompc / (p->hashfraction * sizeof(*p->froms));
     }
 
+    frompcindex = &p->froms[i];
     toindex = *frompcindex;
-
     if (toindex == 0) {
-        /* first time down this arc */
+        /*
+         *	first time traversing this arc
+         */
         toindex = ++p->tos[0].link;
         if (toindex >= p->tolimit)
-            /* Ouch! Overflow */
+            /* halt further profiling */
             goto overflow;
 
-        *frompcindex = (uint16) toindex;
+        *frompcindex = toindex;
         top = &p->tos[toindex];
         top->selfpc = selfpc;
         top->count = 1;
         top->link = 0;
         goto done;
     }
-
     top = &p->tos[toindex];
+
     if (top->selfpc == selfpc) {
-        /* arc at front of chain */
+        /* arc at front of chain; usual case. */
         top->count++;
         goto done;
     }
-
-    for (;;) {
+    /*
+     * have to go looking down chain for it.
+     * top points to what we are looking at,
+     * prevtop points to previous top.
+     * we know it is not at the head of the chain.
+     */
+    for (;; ) {
         if (top->link == 0) {
+            /*
+             * top is end of the chain and none of the chain
+             * had top->selfpc == selfpc.
+             * so we allocate a new tostruct
+             * and link it to the head of the chain.
+             */
             toindex = ++p->tos[0].link;
             if (toindex >= p->tolimit)
                 goto overflow;
@@ -79,17 +96,25 @@ __mcount(uint32 frompc, uint32 selfpc) {
             top->selfpc = selfpc;
             top->count = 1;
             top->link = *frompcindex;
-            *frompcindex = (uint16) toindex;
+            *frompcindex = toindex;
             goto done;
         }
+        /*
+         * otherwise, check the next arc on the chain.
+         */
         prevtop = top;
         top = &p->tos[top->link];
         if (top->selfpc == selfpc) {
+            /*
+             * there it is.
+             * increment its count
+             * move it to the head of the chain.
+             */
             top->count++;
             toindex = prevtop->link;
             prevtop->link = top->link;
             top->link = *frompcindex;
-            *frompcindex = (uint16) toindex;
+            *frompcindex = toindex;
             goto done;
         }
     }