patch-2.4.4 linux/arch/i386/lib/mmx.c

• Lines: 146
• Date: Wed Apr 11 19:02:27 2001
• Orig file: v2.4.3/linux/arch/i386/lib/mmx.c
• Orig date: Thu Mar 1 18:04:34 2001

diff -u --recursive --new-file v2.4.3/linux/arch/i386/lib/mmx.c linux/arch/i386/lib/mmx.c
@@ -1,3 +1,4 @@
+#include <linux/config.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/sched.h>
@@ -5,6 +6,7 @@
 #include <asm/i387.h>
 #include <asm/hardirq.h> 
 
+
 /*
  *	MMX 3DNow! library helper functions
  *
@@ -95,6 +97,13 @@
 	return p;
 }
 
+#ifdef CONFIG_MK7
+
+/*
+ *	The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
+ *	other MMX using processors do not.
+ */
+
 static void fast_clear_page(void *page)
 {
 	int i;
@@ -194,6 +203,118 @@
 	);
 	kernel_fpu_end();
 }
+
+#else
+
+/*
+ *	Generic MMX implementation without K7 specific streaming
+ */
+ 
+static void fast_clear_page(void *page)
+{
+	int i;
+	if (!(current->flags & PF_USEDFPU))
+		clts();
+	else
+	{
+		__asm__ __volatile__ ( " fnsave %0; fwait\n"::"m"(current->thread.i387));
+		current->flags &= ~PF_USEDFPU;
+	}
+	
+	__asm__ __volatile__ (
+		"  pxor %%mm0, %%mm0\n" : :
+	);
+
+	for(i=0;i<4096/128;i++)
+	{
+		__asm__ __volatile__ (
+		"  movq %%mm0, (%0)\n"
+		"  movq %%mm0, 8(%0)\n"
+		"  movq %%mm0, 16(%0)\n"
+		"  movq %%mm0, 24(%0)\n"
+		"  movq %%mm0, 32(%0)\n"
+		"  movq %%mm0, 40(%0)\n"
+		"  movq %%mm0, 48(%0)\n"
+		"  movq %%mm0, 56(%0)\n"
+		"  movq %%mm0, 64(%0)\n"
+		"  movq %%mm0, 72(%0)\n"
+		"  movq %%mm0, 80(%0)\n"
+		"  movq %%mm0, 88(%0)\n"
+		"  movq %%mm0, 96(%0)\n"
+		"  movq %%mm0, 104(%0)\n"
+		"  movq %%mm0, 112(%0)\n"
+		"  movq %%mm0, 120(%0)\n"
+		: : "r" (page) : "memory");
+		page+=128;
+	}
+	stts();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+	int i;
+	if (!(current->flags & PF_USEDFPU))
+		clts();
+	else
+	{
+		__asm__ __volatile__ ( " fnsave %0; fwait\n"::"m"(current->thread.i387));
+		current->flags &= ~PF_USEDFPU;
+	}
+
+	__asm__ __volatile__ (
+		"1: prefetch (%0)\n"
+		"   prefetch 64(%0)\n"
+		"   prefetch 128(%0)\n"
+		"   prefetch 192(%0)\n"
+		"   prefetch 256(%0)\n"
+		"2:  \n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from) );
+
+	for(i=0; i<4096/64; i++)
+	{
+		__asm__ __volatile__ (
+		"1: prefetch 320(%0)\n"
+		"2: movq (%0), %%mm0\n"
+		"   movq 8(%0), %%mm1\n"
+		"   movq 16(%0), %%mm2\n"
+		"   movq 24(%0), %%mm3\n"
+		"   movq %%mm0, (%1)\n"
+		"   movq %%mm1, 8(%1)\n"
+		"   movq %%mm2, 16(%1)\n"
+		"   movq %%mm3, 24(%1)\n"
+		"   movq 32(%0), %%mm0\n"
+		"   movq 40(%0), %%mm1\n"
+		"   movq 48(%0), %%mm2\n"
+		"   movq 56(%0), %%mm3\n"
+		"   movq %%mm0, 32(%1)\n"
+		"   movq %%mm1, 40(%1)\n"
+		"   movq %%mm2, 48(%1)\n"
+		"   movq %%mm3, 56(%1)\n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+	stts();
+}
+
+
+#endif
 
 /*
  *	Favour MMX for page clear and copy.