Use Linux's udelay and ndelay.

It's not very precise to implement udelay and ndelay with loops
in the user space, but should be enough.

2 files changed, 138 insertions, 19 deletions

diff --git a/libdde_linux26/lib/src/arch/l4/timer.c b/libdde_linux26/lib/src/arch/l4/timer.c
index 2b657ab4..b85c83a9 100644
--- a/libdde_linux26/lib/src/arch/l4/timer.c
+++ b/libdde_linux26/lib/src/arch/l4/timer.c
@@ -126,25 +126,6 @@ void msleep(unsigned int msecs)
 	ddekit_thread_msleep(msecs);
 }
 
-
-void __const_udelay(unsigned long xloops)
-{
-	ddekit_thread_usleep(xloops);
-}
-
-
-void __udelay(unsigned long usecs)
-{
-	ddekit_thread_usleep(usecs);
-}
-
-
-void __ndelay(unsigned long nsecs)
-{
-	ddekit_thread_nsleep(nsecs);
-}
-
-
 void __init l4dde26_init_timers(void)
 {
 	ddekit_init_timers();
diff --git a/libdde_linux26/lib/src/arch/x86/lib/delay.c b/libdde_linux26/lib/src/arch/x86/lib/delay.c
new file mode 100644
index 00000000..6097c6bb
--- /dev/null
+++ b/libdde_linux26/lib/src/arch/x86/lib/delay.c
@@ -0,0 +1,138 @@
+/*
+ *	Precise Delay Loops for i386
+ *
+ *	Copyright (C) 1993 Linus Torvalds
+ *	Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *	Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
+ *
+ *	The __delay function must _NOT_ be inlined as its execution time
+ *	depends wildly on alignment on many x86 processors. The additional
+ *	jump magic is needed to get the timing stable on all the CPU's
+ *	we have to worry about.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/timex.h>
+#include <linux/preempt.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+
+#include <asm/processor.h>
+#include <asm/delay.h>
+#include <asm/timer.h>
+
+#ifdef CONFIG_SMP
+# include <asm/smp.h>
+#endif
+#include <ddekit/timer.h>
+
+/* simple loop based delay: */
+static void delay_loop(unsigned long loops)
+{
+	asm volatile(
+		"	test %0,%0	\n"
+		"	jz 3f		\n"
+		"	jmp 1f		\n"
+
+		".align 16		\n"
+		"1:	jmp 2f		\n"
+
+		".align 16		\n"
+		"2:	dec %0		\n"
+		"	jnz 2b		\n"
+		"3:	dec %0		\n"
+
+		: /* we don't need output */
+		:"a" (loops)
+	);
+}
+
+/* TSC based delay: */
+static void delay_tsc(unsigned long loops)
+{
+	unsigned long bclock, now;
+	int cpu;
+
+	preempt_disable();
+	cpu = smp_processor_id();
+	rdtscl(bclock);
+	for (;;) {
+		rdtscl(now);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
+	}
+	preempt_enable();
+}
+
+/*
+ * Since we calibrate only once at boot, this
+ * function should be set once at boot and not changed
+ */
+static void (*delay_fn)(unsigned long) = delay_loop;
+
+void use_tsc_delay(void)
+{
+	delay_fn = delay_tsc;
+}
+
+int __devinit read_current_timer(unsigned long *timer_val)
+{
+	if (delay_fn == delay_tsc) {
+		rdtscll(*timer_val);
+		return 0;
+	}
+	return -1;
+}
+
+void __delay(unsigned long loops)
+{
+	delay_fn(loops);
+}
+EXPORT_SYMBOL(__delay);
+
+inline void __const_udelay(unsigned long xloops)
+{
+	int d0;
+
+	xloops *= 4;
+	asm("mull %%edx"
+		:"=d" (xloops), "=&a" (d0)
+		:"1" (xloops), "0"
+		(loops_per_jiffy * (HZ/4)));
+
+	__delay(++xloops);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);