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.

4 files changed, 322 insertions, 19 deletions

diff --git a/libdde_linux26/lib/src/Makefile b/libdde_linux26/lib/src/Makefile
index ed53fdeb..358196bb 100644
--- a/libdde_linux26/lib/src/Makefile
+++ b/libdde_linux26/lib/src/Makefile
@@ -58,6 +58,7 @@ SRC_C_libdde_linux26.o.a = $(addprefix arch/l4/, $(SRC_DDE))
 
 ifeq ($(ARCH), x86)
 SRC_S_libdde_linux26.o.a += $(ARCH_DIR)/lib/semaphore_32.S
+SRC_S_libdde_linux26.o.a += $(ARCH_DIR)/lib/delay.o
 SRC_C_libdde_linux26.o.a += lib/rwsem.c
 SRC_C_libdde_linux26.o.a += $(ARCH_DIR)/kernel/pci-dma.c
 SRC_C_libdde_linux26.o.a += $(ARCH_DIR)/kernel/pci-nommu.c
@@ -120,6 +121,7 @@ SRC_C_libdde_linux26.o.a += \
 				lib/string.c \
 				lib/vsprintf.c \
 				lib/rbtree.c \
+				init/calibrate.c \
 				mm/dmapool.c \
 				mm/mempool.c \
 				mm/swap.c \
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);
diff --git a/libdde_linux26/lib/src/init/calibrate.c b/libdde_linux26/lib/src/init/calibrate.c
new file mode 100644
index 00000000..aede8e53
--- /dev/null
+++ b/libdde_linux26/lib/src/init/calibrate.c
@@ -0,0 +1,182 @@
+/* calibrate.c: default delay calibration
+ *
+ * Excised from init/main.c
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/timex.h>
+#include <linux/smp.h>
+#include <ddekit/timer.h>
+
+unsigned long loops_per_jiffy = (1<<12);
+EXPORT_SYMBOL(loops_per_jiffy);
+
+unsigned long lpj_fine;
+unsigned long preset_lpj;
+static int __init lpj_setup(char *str)
+{
+	preset_lpj = simple_strtoul(str,NULL,0);
+	return 1;
+}
+
+__setup("lpj=", lpj_setup);
+
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+
+/* This routine uses the read_current_timer() routine and gets the
+ * loops per jiffy directly, instead of guessing it using delay().
+ * Also, this code tries to handle non-maskable asynchronous events
+ * (like SMIs)
+ */
+#define DELAY_CALIBRATION_TICKS			((HZ < 100) ? 1 : (HZ/100))
+#define MAX_DIRECT_CALIBRATION_RETRIES		5
+
+static unsigned long __cpuinit calibrate_delay_direct(void)
+{
+	unsigned long pre_start, start, post_start;
+	unsigned long pre_end, end, post_end;
+	unsigned long start_jiffies;
+	unsigned long timer_rate_min, timer_rate_max;
+	unsigned long good_timer_sum = 0;
+	unsigned long good_timer_count = 0;
+	int i;
+
+	if (read_current_timer(&pre_start) < 0 )
+		return 0;
+
+	/*
+	 * A simple loop like
+	 *	while ( jiffies < start_jiffies+1)
+	 *		start = read_current_timer();
+	 * will not do. As we don't really know whether jiffy switch
+	 * happened first or timer_value was read first. And some asynchronous
+	 * event can happen between these two events introducing errors in lpj.
+	 *
+	 * So, we do
+	 * 1. pre_start <- When we are sure that jiffy switch hasn't happened
+	 * 2. check jiffy switch
+	 * 3. start <- timer value before or after jiffy switch
+	 * 4. post_start <- When we are sure that jiffy switch has happened
+	 *
+	 * Note, we don't know anything about order of 2 and 3.
+	 * Now, by looking at post_start and pre_start difference, we can
+	 * check whether any asynchronous event happened or not
+	 */
+
+	for (i = 0; i < MAX_DIRECT_CALIBRATION_RETRIES; i++) {
+		pre_start = 0;
+		read_current_timer(&start);
+		start_jiffies = jiffies;
+		while (jiffies <= (start_jiffies + 1)) {
+			pre_start = start;
+			read_current_timer(&start);
+		}
+		read_current_timer(&post_start);
+
+		pre_end = 0;
+		end = post_start;
+		while (jiffies <=
+		       (start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) {
+			pre_end = end;
+			read_current_timer(&end);
+		}
+		read_current_timer(&post_end);
+
+		timer_rate_max = (post_end - pre_start) /
+					DELAY_CALIBRATION_TICKS;
+		timer_rate_min = (pre_end - post_start) /
+					DELAY_CALIBRATION_TICKS;
+
+		/*
+		 * If the upper limit and lower limit of the timer_rate is
+		 * >= 12.5% apart, redo calibration.
+		 */
+		if (pre_start != 0 && pre_end != 0 &&
+		    (timer_rate_max - timer_rate_min) < (timer_rate_max >> 3)) {
+			good_timer_count++;
+			good_timer_sum += timer_rate_max;
+		}
+	}
+
+	if (good_timer_count)
+		return (good_timer_sum/good_timer_count);
+
+	printk(KERN_WARNING "calibrate_delay_direct() failed to get a good "
+	       "estimate for loops_per_jiffy.\nProbably due to long platform interrupts. Consider using \"lpj=\" boot option.\n");
+	return 0;
+}
+#else
+static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
+#endif
+
+/*
+ * This is the number of bits of precision for the loops_per_jiffy.  Each
+ * bit takes on average 1.5/HZ seconds.  This (like the original) is a little
+ * better than 1%
+ * For the boot cpu we can skip the delay calibration and assign it a value
+ * calculated based on the timer frequency.
+ * For the rest of the CPUs we cannot assume that the timer frequency is same as
+ * the cpu frequency, hence do the calibration for those.
+ */
+#define LPS_PREC 8
+
+void __cpuinit calibrate_delay(void)
+{
+	unsigned long ticks, loopbit;
+	int lps_precision = LPS_PREC;
+
+	if (preset_lpj) {
+		loops_per_jiffy = preset_lpj;
+		printk(KERN_INFO
+			"Calibrating delay loop (skipped) preset value.. ");
+	} else if ((smp_processor_id() == 0) && lpj_fine) {
+		loops_per_jiffy = lpj_fine;
+		printk(KERN_INFO
+			"Calibrating delay loop (skipped), "
+			"value calculated using timer frequency.. ");
+	} else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) {
+		printk(KERN_INFO
+			"Calibrating delay using timer specific routine.. ");
+	} else {
+		loops_per_jiffy = (1<<12);
+
+		printk(KERN_INFO "Calibrating delay loop... ");
+		while ((loops_per_jiffy <<= 1) != 0) {
+			/* wait for "start of" clock tick */
+			ticks = jiffies;
+			while (ticks == jiffies)
+				/* nothing */;
+			/* Go .. */
+			ticks = jiffies;
+			__delay(loops_per_jiffy);
+			ticks = jiffies - ticks;
+			if (ticks)
+				break;
+		}
+
+		/*
+		 * Do a binary approximation to get loops_per_jiffy set to
+		 * equal one clock (up to lps_precision bits)
+		 */
+		loops_per_jiffy >>= 1;
+		loopbit = loops_per_jiffy;
+		while (lps_precision-- && (loopbit >>= 1)) {
+			loops_per_jiffy |= loopbit;
+			ticks = jiffies;
+			while (ticks == jiffies)
+				/* nothing */;
+			ticks = jiffies;
+			__delay(loops_per_jiffy);
+			if (jiffies != ticks)	/* longer than 1 tick */
+				loops_per_jiffy &= ~loopbit;
+		}
+	}
+	printk(KERN_CONT "%lu.%02lu BogoMIPS (lpj=%lu)\n",
+			loops_per_jiffy/(500000/HZ),
+			(loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
+}
+
+core_initcall(calibrate_delay);