Merge bk://linux.bkbits.net/linux-2.5

into maxwell.earthlink.net:/usr/src/linus-2.5

Documentation/DocBook/Makefile

@@ -162,7 +162,6 @@ LOG     :=      $(patsubst %.sgml, %.log, $(BOOKS))
 OUT     :=      $(patsubst %.sgml, %.out, $(BOOKS))
 
 clean:
-	@rm -f core *~
 	@rm -f $(BOOKS)
 	@rm -f $(DVI) $(AUX) $(TEX) $(LOG) $(OUT)
 	@rm -f $(PNG-parportbook) $(EPS-parportbook)

Makefile

@@ -4,9 +4,9 @@ SUBLEVEL = 41
 EXTRAVERSION =
 
 # *DOCUMENTATION*
-# Too see a list of typical targets execute "make help"
+# To see a list of typical targets execute "make help"
 # More info can be located in ./Documentation/kbuild
-# Comments in this file is targeted only to the developer, do not
+# Comments in this file are targeted only to the developer, do not
 # expect to learn how to build the kernel reading this file.
 
 # We are using a recursive build, so we need to do a little thinking
@@ -142,7 +142,7 @@ NM		= $(CROSS_COMPILE)nm
 STRIP		= $(CROSS_COMPILE)strip
 OBJCOPY		= $(CROSS_COMPILE)objcopy
 OBJDUMP		= $(CROSS_COMPILE)objdump
-MAKEFILES	= $(TOPDIR)/.config
+MAKEFILES	= .config
 GENKSYMS	= /sbin/genksyms
 DEPMOD		= /sbin/depmod
 KALLSYMS	= /sbin/kallsyms
@@ -387,17 +387,17 @@ targets += arch/$(ARCH)/vmlinux.lds.s
 # Single targets
 # ---------------------------------------------------------------------------
 
-%.s: %.c FORCE
+%.s: %.c scripts FORCE
 	+@$(call descend,$(@D),$@)
-%.i: %.c FORCE
+%.i: %.c scripts FORCE
 	+@$(call descend,$(@D),$@)
-%.o: %.c FORCE
+%.o: %.c scripts FORCE
 	+@$(call descend,$(@D),$@)
-%.lst: %.c FORCE
+%.lst: %.c scripts FORCE
 	+@$(call descend,$(@D),$@)
-%.s: %.S FORCE
+%.s: %.S scripts FORCE
 	+@$(call descend,$(@D),$@)
-%.o: %.S FORCE
+%.o: %.S scripts FORCE
 	+@$(call descend,$(@D),$@)
 
 # 	FIXME: The asm symlink changes when $(ARCH) changes. That's
@@ -883,7 +883,7 @@ if_changed_dep = $(if $(strip $? $(filter-out FORCE $(wildcard $^),$^)\
 	@set -e; \
 	$(if $($(quiet)cmd_$(1)),echo '  $($(quiet)cmd_$(1))';) \
 	$(cmd_$(1)); \
-	$(TOPDIR)/scripts/fixdep $(depfile) $@ $(TOPDIR) '$(cmd_$(1))' > $(@D)/.$(@F).tmp; \
+	scripts/fixdep $(depfile) $@ '$(cmd_$(1))' > $(@D)/.$(@F).tmp; \
 	rm -f $(depfile); \
 	mv -f $(@D)/.$(@F).tmp $(@D)/.$(@F).cmd)
 

Rules.make

@@ -209,10 +209,10 @@ define rule_cc_ver_c
 	$(if $($(quiet)cmd_cc_ver_c),echo '  $($(quiet)cmd_cc_ver_c)';) \
 	$(cmd_cc_ver_c); \
 	if [ ! -r $(depfile) ]; then exit 1; fi; \
-	$(TOPDIR)/scripts/fixdep $(depfile) $@ $(TOPDIR) '$(cmd_cc_ver_c)' > $(@D)/.$(@F).tmp; \
+	scripts/fixdep $(depfile) $@ '$(cmd_cc_ver_c)' > $(@D)/.$(@F).tmp; \
 	rm -f $(depfile); \
 	if [ ! -r $@ ] || cmp -s $@ $@.tmp; then \
-	  touch $(TOPDIR)/include/linux/modversions.h; \
+	  touch include/linux/modversions.h; \
 	fi; \
 	mv -f $@.tmp $@
 	mv -f $(@D)/.$(@F).tmp $(@D)/.$(@F).cmd
@@ -312,7 +312,7 @@ cmd_cc_o_c       = $(CC) $(c_flags) -c -o $@ $<
 	$(call if_changed_dep,cc_o_c)
 
 quiet_cmd_cc_lst_c = MKLST   $(echo_target)
-cmd_cc_lst_c       = $(CC) $(c_flags) -g -c -o $*.o $< && $(TOPDIR)/scripts/makelst $*.o $(TOPDIR)/System.map $(OBJDUMP) > $@
+cmd_cc_lst_c       = $(CC) $(c_flags) -g -c -o $*.o $< && sh scripts/makelst $*.o System.map $(OBJDUMP) > $@
 
 %.lst: %.c FORCE
 	$(call if_changed_dep,cc_lst_c)
@@ -561,7 +561,7 @@ if_changed_dep = $(if $(strip $? $(filter-out FORCE $(wildcard $^),$^)\
 	@set -e; \
 	$(if $($(quiet)cmd_$(1)),echo '  $($(quiet)cmd_$(1))';) \
 	$(cmd_$(1)); \
-	$(TOPDIR)/scripts/fixdep $(depfile) $@ $(TOPDIR) '$(cmd_$(1))' > $(@D)/.$(@F).tmp; \
+	scripts/fixdep $(depfile) $@ '$(cmd_$(1))' > $(@D)/.$(@F).tmp; \
 	rm -f $(depfile); \
 	mv -f $(@D)/.$(@F).tmp $(@D)/.$(@F).cmd)
 

arch/i386/Config.help

@@ -65,6 +65,14 @@ CONFIG_X86_NUMAQ
   You will need a new lynxer.elf file to flash your firmware with - send
   email to Martin.Bligh@us.ibm.com
 
+CONFIG_X86_CYCLONE
+  This patch used the Cyclone performance counter on IBM x440, x360,
+  and other Summit based systems for calculating gettimeofday. This 
+  fixes problems resulting from TSC skew found in multi-CEC system. 
+
+  If you are suffering from time skew using a multi-CEC system, say YES.
+  Otherwise it is safe to say NO.
+
 CONFIG_X86_UP_IOAPIC
   An IO-APIC (I/O Advanced Programmable Interrupt Controller) is an
   SMP-capable replacement for PC-style interrupt controllers. Most

arch/i386/Makefile

@@ -52,7 +52,8 @@ endif
 HEAD := arch/i386/kernel/head.o arch/i386/kernel/init_task.o
 
 libs-y 					+= arch/i386/lib/
-core-y					+= arch/i386/kernel/ arch/i386/mm/ \
+core-y					+= arch/i386/kernel/ \
+					   arch/i386/mm/ \
 					   arch/i386/$(MACHINE)/
 drivers-$(CONFIG_MATH_EMULATION)	+= arch/i386/math-emu/
 drivers-$(CONFIG_PCI)			+= arch/i386/pci/

arch/i386/kernel/Makefile

@@ -12,6 +12,7 @@ obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o vm86.o \
 		bootflag.o
 
 obj-y				+= cpu/
+obj-y				+= timers/
 obj-$(CONFIG_X86_BIOS_REBOOT)	+= reboot.o
 obj-$(CONFIG_MCA)		+= mca.o
 obj-$(CONFIG_X86_MSR)		+= msr.o

arch/i386/kernel/timers/Makefile

+#
+# Makefile for x86 timers
+#
+
+obj-y := timer.o
+
+obj-y += timer_tsc.o
+obj-y += timer_pit.o
+obj-$(CONFIG_X86_CYCLONE)   += timer_cyclone.o
+
+include $(TOPDIR)/Rules.make

arch/i386/kernel/timers/timer.c

+#include <linux/kernel.h>
+#include <asm/timer.h>
+
+/* list of externed timers */
+extern struct timer_opts timer_pit;
+extern struct timer_opts timer_tsc;
+
+/* list of timers, ordered by preference, NULL terminated */
+static struct timer_opts* timers[] = {
+	&timer_tsc,
+#ifndef CONFIG_X86_TSC
+	&timer_pit,
+#endif
+	NULL,
+};
+
+
+/* iterates through the list of timers, returning the first 
+ * one that initializes successfully.
+ */
+struct timer_opts* select_timer(void)
+{
+	int i = 0;
+	
+	/* find most preferred working timer */
+	while (timers[i]) {
+		if (timers[i]->init)
+			if (timers[i]->init() == 0)
+				return timers[i];
+		++i;
+	}
+		
+	panic("select_timer: Cannot find a suitable timer\n");
+	return NULL;
+}

arch/i386/kernel/timers/timer_cyclone.c

+/*	Cyclone-timer: 
+ *		This code implements timer_ops for the cyclone counter found
+ *		on IBM x440, x360, and other Summit based systems.
+ *
+ *	Copyright (C) 2002 IBM, John Stultz (johnstul@us.ibm.com)
+ */
+
+
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/timex.h>
+
+#include <asm/timer.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+
+extern spinlock_t i8253_lock;
+
+/* Number of usecs that the last interrupt was delayed */
+static int delay_at_last_interrupt;
+
+#define CYCLONE_CBAR_ADDR 0xFEB00CD0
+#define CYCLONE_PMCC_OFFSET 0x51A0
+#define CYCLONE_MPMC_OFFSET 0x51D0
+#define CYCLONE_MPCS_OFFSET 0x51A8
+#define CYCLONE_TIMER_FREQ 100000000
+
+int use_cyclone = 0;
+
+static u32* volatile cyclone_timer;	/* Cyclone MPMC0 register */
+static u32 last_cyclone_timer;
+
+static void mark_offset_cyclone(void)
+{
+	int count;
+	spin_lock(&i8253_lock);
+	/* quickly read the cyclone timer */
+	if(cyclone_timer)
+		last_cyclone_timer = cyclone_timer[0];
+
+	/* calculate delay_at_last_interrupt */
+	outb_p(0x00, 0x43);     /* latch the count ASAP */
+
+	count = inb_p(0x40);    /* read the latched count */
+	count |= inb(0x40) << 8;
+	spin_unlock(&i8253_lock);
+
+	count = ((LATCH-1) - count) * TICK_SIZE;
+	delay_at_last_interrupt = (count + LATCH/2) / LATCH;
+}
+
+static unsigned long get_offset_cyclone(void)
+{
+	u32 offset;
+
+	if(!cyclone_timer)
+		return delay_at_last_interrupt;
+
+	/* Read the cyclone timer */
+	offset = cyclone_timer[0];
+
+	/* .. relative to previous jiffy */
+	offset = offset - last_cyclone_timer;
+
+	/* convert cyclone ticks to microseconds */	
+	/* XXX slow, can we speed this up? */
+	offset = offset/(CYCLONE_TIMER_FREQ/1000000);
+
+	/* our adjusted time offset in microseconds */
+	return delay_at_last_interrupt + offset;
+}
+
+static int init_cyclone(void)
+{
+	u32* reg;	
+	u32 base;		/* saved cyclone base address */
+	u32 pageaddr;	/* page that contains cyclone_timer register */
+	u32 offset;		/* offset from pageaddr to cyclone_timer register */
+	int i;
+	
+	/*make sure we're on a summit box*/
+	/*XXX need to use proper summit hooks! such as xapic -john*/
+	if(!use_cyclone) return 0; 
+	
+	printk(KERN_INFO "Summit chipset: Starting Cyclone Counter.\n");
+
+	/* find base address */
+	pageaddr = (CYCLONE_CBAR_ADDR)&PAGE_MASK;
+	offset = (CYCLONE_CBAR_ADDR)&(~PAGE_MASK);
+	set_fixmap_nocache(FIX_CYCLONE_TIMER, pageaddr);
+	reg = (u32*)(fix_to_virt(FIX_CYCLONE_TIMER) + offset);
+	if(!reg){
+		printk(KERN_ERR "Summit chipset: Could not find valid CBAR register.\n");
+		return 0;
+	}
+	base = *reg;	
+	if(!base){
+		printk(KERN_ERR "Summit chipset: Could not find valid CBAR value.\n");
+		return 0;
+	}
+	
+	/* setup PMCC */
+	pageaddr = (base + CYCLONE_PMCC_OFFSET)&PAGE_MASK;
+	offset = (base + CYCLONE_PMCC_OFFSET)&(~PAGE_MASK);
+	set_fixmap_nocache(FIX_CYCLONE_TIMER, pageaddr);
+	reg = (u32*)(fix_to_virt(FIX_CYCLONE_TIMER) + offset);
+	if(!reg){
+		printk(KERN_ERR "Summit chipset: Could not find valid PMCC register.\n");
+		return 0;
+	}
+	reg[0] = 0x00000001;
+
+	/* setup MPCS */
+	pageaddr = (base + CYCLONE_MPCS_OFFSET)&PAGE_MASK;
+	offset = (base + CYCLONE_MPCS_OFFSET)&(~PAGE_MASK);
+	set_fixmap_nocache(FIX_CYCLONE_TIMER, pageaddr);
+	reg = (u32*)(fix_to_virt(FIX_CYCLONE_TIMER) + offset);
+	if(!reg){
+		printk(KERN_ERR "Summit chipset: Could not find valid MPCS register.\n");
+		return 0;
+	}
+	reg[0] = 0x00000001;
+
+	/* map in cyclone_timer */
+	pageaddr = (base + CYCLONE_MPMC_OFFSET)&PAGE_MASK;
+	offset = (base + CYCLONE_MPMC_OFFSET)&(~PAGE_MASK);
+	set_fixmap_nocache(FIX_CYCLONE_TIMER, pageaddr);
+	cyclone_timer = (u32*)(fix_to_virt(FIX_CYCLONE_TIMER) + offset);
+	if(!cyclone_timer){
+		printk(KERN_ERR "Summit chipset: Could not find valid MPMC register.\n");
+		return 0;
+	}
+
+	/*quick test to make sure its ticking*/
+	for(i=0; i<3; i++){
+		u32 old = cyclone_timer[0];
+		int stall = 100;
+		while(stall--) barrier();
+		if(cyclone_timer[0] == old){
+			printk(KERN_ERR "Summit chipset: Counter not counting! DISABLED\n");
+			cyclone_timer = 0;
+			return 0;
+		}
+	}
+
+	/* Everything looks good! */
+	return 1;
+}
+
+
+#if 0 /* XXX future work */
+static void delay_cyclone(unsigned long loops)
+{
+	unsigned long bclock, now;
+	if(!cyclone_timer)
+		return;
+	bclock = cyclone_timer[0];
+	do {
+		rep_nop();
+		now = cyclone_timer[0];
+	} while ((now-bclock) < loops);
+}
+#endif
+/************************************************************/
+
+/* cyclone timer_opts struct */
+struct timer_opts timer_cyclone = {
+	init: init_cyclone, 
+	mark_offset: mark_offset_cyclone, 
+	get_offset: get_offset_cyclone
+};

arch/i386/kernel/timers/timer_pit.c

+/*
+ * This code largely moved from arch/i386/kernel/time.c.
+ * See comments there for proper credits.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <asm/timer.h>
+#include <asm/io.h>
+
+extern spinlock_t i8259A_lock;
+extern spinlock_t i8253_lock;
+#include "do_timer.h"
+
+static int init_pit(void)
+{
+	return 0;
+}
+
+static void mark_offset_pit(void)
+{
+	/* nothing needed */
+}
+
+
+/* This function must be called with interrupts disabled 
+ * It was inspired by Steve McCanne's microtime-i386 for BSD.  -- jrs
+ * 
+ * However, the pc-audio speaker driver changes the divisor so that
+ * it gets interrupted rather more often - it loads 64 into the
+ * counter rather than 11932! This has an adverse impact on
+ * do_gettimeoffset() -- it stops working! What is also not
+ * good is that the interval that our timer function gets called
+ * is no longer 10.0002 ms, but 9.9767 ms. To get around this
+ * would require using a different timing source. Maybe someone
+ * could use the RTC - I know that this can interrupt at frequencies
+ * ranging from 8192Hz to 2Hz. If I had the energy, I'd somehow fix
+ * it so that at startup, the timer code in sched.c would select
+ * using either the RTC or the 8253 timer. The decision would be
+ * based on whether there was any other device around that needed
+ * to trample on the 8253. I'd set up the RTC to interrupt at 1024 Hz,
+ * and then do some jiggery to have a version of do_timer that 
+ * advanced the clock by 1/1024 s. Every time that reached over 1/100
+ * of a second, then do all the old code. If the time was kept correct
+ * then do_gettimeoffset could just return 0 - there is no low order
+ * divider that can be accessed.
+ *
+ * Ideally, you would be able to use the RTC for the speaker driver,
+ * but it appears that the speaker driver really needs interrupt more
+ * often than every 120 us or so.
+ *
+ * Anyway, this needs more thought....		pjsg (1993-08-28)
+ * 
+ * If you are really that interested, you should be reading
+ * comp.protocols.time.ntp!
+ */
+
+static unsigned long get_offset_pit(void)
+{
+	int count;
+
+	static int count_p = LATCH;    /* for the first call after boot */
+	static unsigned long jiffies_p = 0;
+
+	/*
+	 * cache volatile jiffies temporarily; we have IRQs turned off. 
+	 */
+	unsigned long jiffies_t;
+
+	/* gets recalled with irq locally disabled */
+	spin_lock(&i8253_lock);
+	/* timer count may underflow right here */
+	outb_p(0x00, 0x43);	/* latch the count ASAP */
+
+	count = inb_p(0x40);	/* read the latched count */
+
+	/*
+	 * We do this guaranteed double memory access instead of a _p 
+	 * postfix in the previous port access. Wheee, hackady hack
+	 */
+ 	jiffies_t = jiffies;
+
+	count |= inb_p(0x40) << 8;
+	
+        /* VIA686a test code... reset the latch if count > max + 1 */
+        if (count > LATCH) {
+                outb_p(0x34, 0x43);
+                outb_p(LATCH & 0xff, 0x40);
+                outb(LATCH >> 8, 0x40);
+                count = LATCH - 1;
+        }
+	
+	spin_unlock(&i8253_lock);
+
+	/*
+	 * avoiding timer inconsistencies (they are rare, but they happen)...
+	 * there are two kinds of problems that must be avoided here:
+	 *  1. the timer counter underflows
+	 *  2. hardware problem with the timer, not giving us continuous time,
+	 *     the counter does small "jumps" upwards on some Pentium systems,
+	 *     (see c't 95/10 page 335 for Neptun bug.)
+	 */
+
+
+	if( jiffies_t == jiffies_p ) {
+		if( count > count_p ) {
+			/* the nutcase */
+			count = do_timer_overflow(count);
+		}
+	} else
+		jiffies_p = jiffies_t;
+
+	count_p = count;
+
+	count = ((LATCH-1) - count) * TICK_SIZE;
+	count = (count + LATCH/2) / LATCH;
+
+	return count;
+}
+
+
+/* tsc timer_opts struct */
+struct timer_opts timer_pit = {
+	.init =		init_pit, 
+	.mark_offset =	mark_offset_pit, 
+	.get_offset =	get_offset_pit,
+};

arch/i386/kernel/timers/timer_tsc.c

+/*
+ * This code largely moved from arch/i386/kernel/time.c.
+ * See comments there for proper credits.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/timex.h>
+#include <linux/errno.h>
+
+#include <asm/timer.h>
+#include <asm/io.h>
+
+extern int x86_udelay_tsc;
+extern spinlock_t i8253_lock;
+
+static int use_tsc;
+/* Number of usecs that the last interrupt was delayed */
+static int delay_at_last_interrupt;
+
+static unsigned long last_tsc_low; /* lsb 32 bits of Time Stamp Counter */
+
+/* Cached *multiplier* to convert TSC counts to microseconds.
+ * (see the equation below).
+ * Equal to 2^32 * (1 / (clocks per usec) ).
+ * Initialized in time_init.
+ */
+unsigned long fast_gettimeoffset_quotient;
+
+static unsigned long get_offset_tsc(void)
+{
+	register unsigned long eax, edx;
+
+	/* Read the Time Stamp Counter */
+
+	rdtsc(eax,edx);
+
+	/* .. relative to previous jiffy (32 bits is enough) */
+	eax -= last_tsc_low;	/* tsc_low delta */
+
+	/*
+         * Time offset = (tsc_low delta) * fast_gettimeoffset_quotient
+         *             = (tsc_low delta) * (usecs_per_clock)
+         *             = (tsc_low delta) * (usecs_per_jiffy / clocks_per_jiffy)
+	 *
+	 * Using a mull instead of a divl saves up to 31 clock cycles
+	 * in the critical path.
+         */
+
+	__asm__("mull %2"
+		:"=a" (eax), "=d" (edx)
+		:"rm" (fast_gettimeoffset_quotient),
+		 "0" (eax));
+
+	/* our adjusted time offset in microseconds */
+	return delay_at_last_interrupt + edx;
+}
+
+static void mark_offset_tsc(void)
+{
+	int count;
+	/*
+	 * It is important that these two operations happen almost at
+	 * the same time. We do the RDTSC stuff first, since it's
+	 * faster. To avoid any inconsistencies, we need interrupts
+	 * disabled locally.
+	 */
+
+	/*
+	 * Interrupts are just disabled locally since the timer irq
+	 * has the SA_INTERRUPT flag set. -arca
+	 */
+	
+	/* read Pentium cycle counter */
+
+	rdtscl(last_tsc_low);
+
+	spin_lock(&i8253_lock);
+	outb_p(0x00, 0x43);     /* latch the count ASAP */
+
+	count = inb_p(0x40);    /* read the latched count */
+	count |= inb(0x40) << 8;
+	spin_unlock(&i8253_lock);
+
+	count = ((LATCH-1) - count) * TICK_SIZE;
+	delay_at_last_interrupt = (count + LATCH/2) / LATCH;
+}
+
+
+/* ------ Calibrate the TSC ------- 
+ * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset().
+ * Too much 64-bit arithmetic here to do this cleanly in C, and for
+ * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2)
+ * output busy loop as low as possible. We avoid reading the CTC registers
+ * directly because of the awkward 8-bit access mechanism of the 82C54
+ * device.
+ */
+
+#define CALIBRATE_LATCH	(5 * LATCH)
+#define CALIBRATE_TIME	(5 * 1000020/HZ)
+
+static unsigned long __init calibrate_tsc(void)
+{
+       /* Set the Gate high, disable speaker */
+	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+	/*
+	 * Now let's take care of CTC channel 2
+	 *
+	 * Set the Gate high, program CTC channel 2 for mode 0,
+	 * (interrupt on terminal count mode), binary count,
+	 * load 5 * LATCH count, (LSB and MSB) to begin countdown.
+	 */
+	outb(0xb0, 0x43);			/* binary, mode 0, LSB/MSB, Ch 2 */
+	outb(CALIBRATE_LATCH & 0xff, 0x42);	/* LSB of count */
+	outb(CALIBRATE_LATCH >> 8, 0x42);	/* MSB of count */
+
+	{
+		unsigned long startlow, starthigh;
+		unsigned long endlow, endhigh;
+		unsigned long count;
+
+		rdtsc(startlow,starthigh);
+		count = 0;
+		do {
+			count++;
+		} while ((inb(0x61) & 0x20) == 0);
+		rdtsc(endlow,endhigh);
+
+		last_tsc_low = endlow;
+
+		/* Error: ECTCNEVERSET */
+		if (count <= 1)
+			goto bad_ctc;
+
+		/* 64-bit subtract - gcc just messes up with long longs */
+		__asm__("subl %2,%0\n\t"
+			"sbbl %3,%1"
+			:"=a" (endlow), "=d" (endhigh)
+			:"g" (startlow), "g" (starthigh),
+			 "0" (endlow), "1" (endhigh));
+
+		/* Error: ECPUTOOFAST */
+		if (endhigh)
+			goto bad_ctc;
+
+		/* Error: ECPUTOOSLOW */
+		if (endlow <= CALIBRATE_TIME)
+			goto bad_ctc;
+
+		__asm__("divl %2"
+			:"=a" (endlow), "=d" (endhigh)
+			:"r" (endlow), "0" (0), "1" (CALIBRATE_TIME));
+
+		return endlow;
+	}
+
+	/*
+	 * The CTC wasn't reliable: we got a hit on the very first read,
+	 * or the CPU was so fast/slow that the quotient wouldn't fit in
+	 * 32 bits..
+	 */
+bad_ctc:
+	return 0;
+}
+
+
+#ifdef CONFIG_CPU_FREQ
+
+static int
+time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+		       void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	unsigned int i;
+
+	if (!cpu_has_tsc)
+		return 0;
+
+	switch (val) {
+	case CPUFREQ_PRECHANGE:
+		if ((freq->old < freq->new) &&
+		((freq->cpu == CPUFREQ_ALL_CPUS) || (freq->cpu == 0)))  {
+			cpu_khz = cpufreq_scale(cpu_khz, freq->old, freq->new);
+		        fast_gettimeoffset_quotient = cpufreq_scale(fast_gettimeoffset_quotient, freq->new, freq->old);
+		}
+		for (i=0; i<NR_CPUS; i++)
+			if ((freq->cpu == CPUFREQ_ALL_CPUS) || (freq->cpu == i))
+				cpu_data[i].loops_per_jiffy = cpufreq_scale(cpu_data[i].loops_per_jiffy, freq->old, freq->new);
+		break;
+
+	case CPUFREQ_POSTCHANGE:
+		if ((freq->new < freq->old) &&
+		((freq->cpu == CPUFREQ_ALL_CPUS) || (freq->cpu == 0)))  {
+			cpu_khz = cpufreq_scale(cpu_khz, freq->old, freq->new);
+		        fast_gettimeoffset_quotient = cpufreq_scale(fast_gettimeoffset_quotient, freq->new, freq->old);
+		}
+		for (i=0; i<NR_CPUS; i++)
+			if ((freq->cpu == CPUFREQ_ALL_CPUS) || (freq->cpu == i))
+				cpu_data[i].loops_per_jiffy = cpufreq_scale(cpu_data[i].loops_per_jiffy, freq->old, freq->new);
+		break;
+	}
+
+	return 0;
+}
+
+static struct notifier_block time_cpufreq_notifier_block = {
+	notifier_call:	time_cpufreq_notifier
+};
+#endif
+
+
+static int init_tsc(void)
+{
+	/*
+	 * If we have APM enabled or the CPU clock speed is variable
+	 * (CPU stops clock on HLT or slows clock to save power)
+	 * then the TSC timestamps may diverge by up to 1 jiffy from
+	 * 'real time' but nothing will break.
+	 * The most frequent case is that the CPU is "woken" from a halt
+	 * state by the timer interrupt itself, so we get 0 error. In the
+	 * rare cases where a driver would "wake" the CPU and request a
+	 * timestamp, the maximum error is < 1 jiffy. But timestamps are
+	 * still perfectly ordered.
+	 * Note that the TSC counter will be reset if APM suspends
+	 * to disk; this won't break the kernel, though, 'cuz we're
+	 * smart.  See arch/i386/kernel/apm.c.
+	 */
+ 	/*
+ 	 *	Firstly we have to do a CPU check for chips with
+ 	 * 	a potentially buggy TSC. At this point we haven't run
+ 	 *	the ident/bugs checks so we must run this hook as it
+ 	 *	may turn off the TSC flag.
+ 	 *
+ 	 *	NOTE: this doesnt yet handle SMP 486 machines where only
+ 	 *	some CPU's have a TSC. Thats never worked and nobody has
+ 	 *	moaned if you have the only one in the world - you fix it!
+ 	 */
+ 
+ 	dodgy_tsc();
+ 	
+	if (cpu_has_tsc) {
+		unsigned long tsc_quotient = calibrate_tsc();
+		if (tsc_quotient) {
+			fast_gettimeoffset_quotient = tsc_quotient;
+			use_tsc = 1;
+			/*
+			 *	We could be more selective here I suspect
+			 *	and just enable this for the next intel chips ?
+			 */
+			x86_udelay_tsc = 1;
+
+			/* report CPU clock rate in Hz.
+			 * The formula is (10^6 * 2^32) / (2^32 * 1 / (clocks/us)) =
+			 * clock/second. Our precision is about 100 ppm.
+			 */
+			{	unsigned long eax=0, edx=1000;
+				__asm__("divl %2"
+		       		:"=a" (cpu_khz), "=d" (edx)
+        	       		:"r" (tsc_quotient),
+	                	"0" (eax), "1" (edx));
+				printk("Detected %lu.%03lu MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000);
+			}
+#ifdef CONFIG_CPU_FREQ
+			cpufreq_register_notifier(&time_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER);
+#endif
+			return 0;
+		}
+	}
+	return -ENODEV;
+}
+
+/************************************************************/
+
+/* tsc timer_opts struct */
+struct timer_opts timer_tsc = {
+	.init =		init_tsc,
+	.mark_offset =	mark_offset_tsc, 
+	.get_offset =	get_offset_tsc,
+};

drivers/cdrom/cdrom.c

@@ -689,21 +689,28 @@ static int cdrom_read_mech_status(struct cdrom_device_info *cdi,
 
 static int cdrom_slot_status(struct cdrom_device_info *cdi, int slot)
 {
-	struct cdrom_changer_info info;
+	struct cdrom_changer_info *info;
 	int ret;
 
 	cdinfo(CD_CHANGER, "entering cdrom_slot_status()\n"); 
 	if (cdi->sanyo_slot)
 		return CDS_NO_INFO;
 	
-	if ((ret = cdrom_read_mech_status(cdi, &info)))
-		return ret;
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	if ((ret = cdrom_read_mech_status(cdi, info)))
+		goto out_free;
 
-	if (info.slots[slot].disc_present)
-		return CDS_DISC_OK;
+	if (info->slots[slot].disc_present)
+		ret = CDS_DISC_OK;
 	else
-		return CDS_NO_DISC;
+		ret = CDS_NO_DISC;
 
+out_free:
+	kfree(info);
+	return ret;
 }
 
 /* Return the number of slots for an ATAPI/SCSI cdrom, 
@@ -713,15 +720,20 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi)
 {
 	int status;
 	int nslots = 1;
-	struct cdrom_changer_info info;
+	struct cdrom_changer_info *info;
 
 	cdinfo(CD_CHANGER, "entering cdrom_number_of_slots()\n"); 
 	/* cdrom_read_mech_status requires a valid value for capacity: */
 	cdi->capacity = 0; 
 
-	if ((status = cdrom_read_mech_status(cdi, &info)) == 0)
-		nslots = info.hdr.nslots;
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	if ((status = cdrom_read_mech_status(cdi, info)) == 0)
+		nslots = info->hdr.nslots;
 
+	kfree(info);
 	return nslots;
 }
 
@@ -755,7 +767,7 @@ static int cdrom_load_unload(struct cdrom_device_info *cdi, int slot)
 
 static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot)
 {
-	struct cdrom_changer_info info;
+	struct cdrom_changer_info *info;
 	int curslot;
 	int ret;
 
@@ -771,10 +783,17 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot)
 		return cdrom_load_unload(cdi, -1);
 	}
 
-	if ((ret = cdrom_read_mech_status(cdi, &info)))
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	if ((ret = cdrom_read_mech_status(cdi, info))) {
+		kfree(info);
 		return ret;
+	}
 
-	curslot = info.hdr.curslot;
+	curslot = info->hdr.curslot;
+	kfree(info);
 
 	if (cdi->use_count > 1 || keeplocked) {
 		if (slot == CDSL_CURRENT) {
@@ -1502,7 +1521,8 @@ int cdrom_ioctl(struct inode *ip, struct file *fp, unsigned int cmd,
 		}
 
 	case CDROM_MEDIA_CHANGED: {
-		struct cdrom_changer_info info;
+		struct cdrom_changer_info *info;
+		int changed;
 
 		cdinfo(CD_DO_IOCTL, "entering CDROM_MEDIA_CHANGED\n"); 
 		if (!CDROM_CAN(CDC_MEDIA_CHANGED))
@@ -1515,10 +1535,18 @@ int cdrom_ioctl(struct inode *ip, struct file *fp, unsigned int cmd,
 		if ((unsigned int)arg >= cdi->capacity)
 			return -EINVAL;
 
-		if ((ret = cdrom_read_mech_status(cdi, &info)))
+		info = kmalloc(sizeof(*info), GFP_KERNEL);
+		if (!info)
+			return -ENOMEM;
+
+		if ((ret = cdrom_read_mech_status(cdi, info))) {
+			kfree(info);
 			return ret;
+		}
 
-		return info.slots[arg].change;
+		changed = info->slots[arg].change;
+		kfree(info);
+		return changed;
 		}
 
 	case CDROM_SET_OPTIONS: {

drivers/scsi/Makefile

@@ -137,7 +137,7 @@ include $(TOPDIR)/Rules.make
 $(obj)/53c7,8xx.o: $(obj)/53c8xx_d.h $(obj)/53c8xx_u.h
 $(obj)/53c7xx.o:   $(obj)/53c7xx_d.h $(obj)/53c7xx_u.h
 $(obj)/sim710.o:   $(obj)/sim710_d.h
-$(obj)/53c700.o $(MODVERDIR)/53c700.ver: $(obj)/53c700_d.h
+$(obj)/53c700.o $(MODVERDIR)/$(obj)/53c700.ver: $(obj)/53c700_d.h
 
 # If you want to play with the firmware, uncomment
 # GENERATE_FIRMWARE := 1

drivers/scsi/aacraid/Makefile

-
-EXTRA_CFLAGS	+= -I$(TOPDIR)/drivers/scsi
+# Adaptec aacraid
  
 obj-$(CONFIG_SCSI_AACRAID) := aacraid.o
 

drivers/scsi/atp870u.c

@@ -902,10 +902,12 @@ static void tscam(struct Scsi_Host *host)
 		0x38, 0x31, 0x32, 0x2b, 0x34, 0x2d, 0x2e, 0x27
 	};
 
-
+/*  I can't believe we need this before we've even done anything.  Remove it
+ *  and see if anyone bitches.
 	for (i = 0; i < 0x10; i++) {
 		udelay(0xffff);
 	}
+ */
 
 	tmport = dev->ioport + 1;
 	outb(0x08, tmport++);
@@ -993,8 +995,7 @@ static void tscam(struct Scsi_Host *host)
 	inb(0x80);		/* 2 deskew delay(45ns*2=90ns) */
 	val &= 0x007f;		/* no bsy  */
 	outw(val, tmport);
-	udelay(0xffff);		/* recommanded SCAM selection response time */
-	udelay(0xffff);
+	mdelay(128);
 	val &= 0x00fb;		/* after 1ms no msg */
 	outw(val, tmport);
 wait_nomsg:
@@ -2420,9 +2421,9 @@ static int atp870u_detect(Scsi_Host_Template * tpnt)
 			k = (inb(tmport) & 0xf3) | 0x10;
 			outb(k, tmport);
 			outb((k & 0xdf), tmport);
-			udelay(0x8000);
+			mdelay(32);
 			outb(k, tmport);
-			udelay(0x8000);
+			mdelay(32);
 			tmport = base_io;
 			outb((host_id | 0x08), tmport);
 			tmport += 0x18;
@@ -2539,9 +2540,9 @@ static int atp870u_detect(Scsi_Host_Template * tpnt)
 			outb(k, tmport);
 			tmport += 0x03;
 			outb(0x20, tmport);
-			udelay(0x8000);
+			mdelay(32);
 			outb(0, tmport);
-			udelay(0x8000);
+			mdelay(32);
 			tmport = base_io + 0x5b;
 			inb(tmport);
 			tmport -= 0x04;
@@ -2581,7 +2582,7 @@ static int atp870u_detect(Scsi_Host_Template * tpnt)
 			shpnt->n_io_port = 0x40;	/* Number of bytes of I/O space used */
 		}
 		shpnt->irq = irq;
-		restore_flags(flags);
+		spin_unlock_irqrestore(shpnt->host_lock, flags);
 		if (dev_id[h] == 0x8081) {
 			request_region(base_io, 0x60, "atp870u");	/* Register the IO ports that we use */
 		} else {

fs/isofs/inode.c

@@ -34,11 +34,6 @@
 
 #include "zisofs.h"
 
-/*
- * We have no support for "multi volume" CDs, but more and more disks carry
- * wrong information within the volume descriptors.
- */
-#define IGNORE_WRONG_MULTI_VOLUME_SPECS
 #define BEQUIET
 
 #ifdef LEAK_CHECK
@@ -556,19 +551,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 	if (!parse_options((char *) data, &opt))
 		goto out_freesbi;
 
-#if 0
-	printk("map = %c\n", opt.map);
-	printk("rock = %c\n", opt.rock);
-	printk("joliet = %c\n", opt.joliet);
-	printk("check = %c\n", opt.check);
-	printk("cruft = %c\n", opt.cruft);
-	printk("unhide = %c\n", opt.unhide);
-	printk("blocksize = %d\n", opt.blocksize);
-	printk("gid = %d\n", opt.gid);
-	printk("uid = %d\n", opt.uid);
-	printk("iocharset = %s\n", opt.iocharset);
-#endif
-
 	/*
 	 * First of all, get the hardware blocksize for this device.
 	 * If we don't know what it is, or the hardware blocksize is
@@ -673,19 +655,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 
 	if(sbi->s_high_sierra){
 	  rootp = (struct iso_directory_record *) h_pri->root_directory_record;
-#ifndef IGNORE_WRONG_MULTI_VOLUME_SPECS
-	  if (isonum_723 (h_pri->volume_set_size) != 1)
-		goto out_no_support;
-#endif /* IGNORE_WRONG_MULTI_VOLUME_SPECS */
 	  sbi->s_nzones = isonum_733 (h_pri->volume_space_size);
 	  sbi->s_log_zone_size = isonum_723 (h_pri->logical_block_size);
 	  sbi->s_max_size = isonum_733(h_pri->volume_space_size);
 	} else {
 	  rootp = (struct iso_directory_record *) pri->root_directory_record;
-#ifndef IGNORE_WRONG_MULTI_VOLUME_SPECS
-	  if (isonum_723 (pri->volume_set_size) != 1)
-		goto out_no_support;
-#endif /* IGNORE_WRONG_MULTI_VOLUME_SPECS */
 	  sbi->s_nzones = isonum_733 (pri->volume_space_size);
 	  sbi->s_log_zone_size = isonum_723 (pri->logical_block_size);
 	  sbi->s_max_size = isonum_733(pri->volume_space_size);
@@ -898,11 +872,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 	printk(KERN_WARNING "Logical zone size(%d) < hardware blocksize(%u)\n",
 		orig_zonesize, opt.blocksize);
 	goto out_freebh;
-#ifndef IGNORE_WRONG_MULTI_VOLUME_SPECS
-out_no_support:
-	printk(KERN_WARNING "Multi-volume disks not supported.\n");
-	goto out_freebh;
-#endif
 out_unknown_format:
 	if (!silent)
 		printk(KERN_WARNING "Unable to identify CD-ROM format.\n");
@@ -1335,28 +1304,7 @@ static void isofs_read_inode(struct inode * inode)
 	/* get the volume sequence number */
 	volume_seq_no = isonum_723 (de->volume_sequence_number) ;
 
-	/*
-	 * Disable checking if we see any volume number other than 0 or 1.
-	 * We could use the cruft option, but that has multiple purposes, one
-	 * of which is limiting the file size to 16Mb.  Thus we silently allow
-	 * volume numbers of 0 to go through without complaining.
-	 */
-	if (sbi->s_cruft == 'n' &&
-	    (volume_seq_no != 0) && (volume_seq_no != 1)) {
-		printk(KERN_WARNING "Warning: defective CD-ROM "
-		       "(volume sequence number %d). "
-		       "Enabling \"cruft\" mount option.\n", volume_seq_no);
-		sbi->s_cruft = 'y';
-	}
-
 	/* Install the inode operations vector */
-#ifndef IGNORE_WRONG_MULTI_VOLUME_SPECS
-	if (sbi->s_cruft != 'y' &&
-	    (volume_seq_no != 0) && (volume_seq_no != 1)) {
-		printk(KERN_WARNING "Multi-volume CD somehow got mounted.\n");
-	} else
-#endif /*IGNORE_WRONG_MULTI_VOLUME_SPECS */
-	{
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_fop = &generic_ro_fops;
 		switch ( ei->i_file_format ) {
@@ -1379,7 +1327,7 @@ static void isofs_read_inode(struct inode * inode)
 		/* XXX - parse_rock_ridge_inode() had already set i_rdev. */
 		init_special_inode(inode, inode->i_mode,
 				   kdev_t_to_nr(inode->i_rdev));
-	}
+
  out:
 	if (tmpde)
 		kfree(tmpde);

fs/nfs/dir.c

@@ -107,7 +107,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
 	dfprintk(VFS, "NFS: nfs_readdir_filler() reading cookie %Lu into page %lu.\n", (long long)desc->entry->cookie, page->index);
 
  again:
-	error = NFS_PROTO(inode)->readdir(inode, cred, desc->entry->cookie, page,
+	error = NFS_PROTO(inode)->readdir(file->f_dentry, cred, desc->entry->cookie, page,
 					  NFS_SERVER(inode)->dtsize, desc->plus);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
@@ -341,7 +341,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 		status = -ENOMEM;
 		goto out;
 	}
-	desc->error = NFS_PROTO(inode)->readdir(inode, cred, desc->target,
+	desc->error = NFS_PROTO(inode)->readdir(file->f_dentry, cred, desc->target,
 						page,
 						NFS_SERVER(inode)->dtsize,
 						desc->plus);
@@ -1022,16 +1022,23 @@ nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	struct nfs_fattr sym_attr;
 	struct nfs_fh sym_fh;
 	struct qstr qsymname;
-	unsigned int maxlen;
 	int error;
 
 	dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry->d_name.name, symname);
 
 	error = -ENAMETOOLONG;
-	maxlen = (NFS_PROTO(dir)->version==2) ? NFS2_MAXPATHLEN : NFS3_MAXPATHLEN;
-	if (strlen(symname) > maxlen)
+	switch (NFS_PROTO(dir)->version) {
+		case 2:
+			if (strlen(symname) > NFS2_MAXPATHLEN)
 				goto out;
+			break;
+		case 3:
+			if (strlen(symname) > NFS3_MAXPATHLEN)
+				goto out;
+		default:
+			break;
+	}
 
 #ifdef NFS_PARANOIA
 if (dentry->d_inode)

fs/nfs/flushd.c

@@ -171,7 +171,7 @@ nfs_flushd(struct rpc_task *task)
 			nfs_pagein_list(&head, server->rpages);
 			continue;
 		}
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 		if (nfs_scan_lru_commit_timeout(server, &head)) {
 			spin_unlock(&nfs_wreq_lock);
 			nfs_commit_list(&head, FLUSH_AGING);

fs/nfs/inode.c

@@ -716,12 +716,14 @@ __nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode->i_mtime = nfs_time_to_secs(new_mtime);
 		NFS_MTIME_UPDATE(inode) = fattr->timestamp;
 		NFS_CACHE_ISIZE(inode) = new_size;
+		if (fattr->valid & NFS_ATTR_FATTR_V4)
+			NFS_CHANGE_ATTR(inode) = fattr->change_attr;
 		inode->i_size = new_isize;
 		inode->i_mode = fattr->mode;
 		inode->i_nlink = fattr->nlink;
 		inode->i_uid = fattr->uid;
 		inode->i_gid = fattr->gid;
-		if (fattr->valid & NFS_ATTR_FATTR_V3) {
+		if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
 			/*
 			 * report the blocks in 512byte units
 			 */
@@ -781,7 +783,7 @@ printk("nfs_setattr: revalidate failed, error=%d\n", error);
 	if (error)
 		goto out;
 
-	error = NFS_PROTO(inode)->setattr(inode, &fattr, attr);
+	error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
 	if (error)
 		goto out;
 	/*
@@ -1067,12 +1069,25 @@ __nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 		invalid = 1;
 	}
 
+	if ((fattr->valid & NFS_ATTR_FATTR_V4)
+	    && NFS_CHANGE_ATTR(inode) != fattr->change_attr) {
+#ifdef NFS_DEBUG_VERBOSE
+		printk(KERN_DEBUG "NFS: change_attr change on %s/%ld\n",
+		       inode->i_sb->s_id, inode->i_ino);
+#endif
+		invalid = 1;
+	}
+
 	/* Check Weak Cache Consistency data.
 	 * If size and mtime match the pre-operation values, we can
 	 * assume that any attribute changes were caused by our NFS
          * operation, so there's no need to invalidate the caches.
          */
-        if ((fattr->valid & NFS_ATTR_WCC)
+	if ((fattr->valid & NFS_ATTR_PRE_CHANGE)
+	    && NFS_CHANGE_ATTR(inode) == fattr->pre_change_attr) {
+		invalid = 0;
+	}
+	else if ((fattr->valid & NFS_ATTR_WCC)
 	    && NFS_CACHE_ISIZE(inode) == fattr->pre_size
 	    && NFS_CACHE_MTIME(inode) == fattr->pre_mtime) {
 		invalid = 0;
@@ -1110,12 +1125,15 @@ __nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 		}
 	}
 
+	if (fattr->valid & NFS_ATTR_FATTR_V4)
+		NFS_CHANGE_ATTR(inode) = fattr->change_attr;
+
 	inode->i_mode = fattr->mode;
 	inode->i_nlink = fattr->nlink;
 	inode->i_uid = fattr->uid;
 	inode->i_gid = fattr->gid;
 
-	if (fattr->valid & NFS_ATTR_FATTR_V3) {
+	if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
 		/*
 		 * report the blocks in 512byte units
 		 */

fs/nfs/nfs2xdr.c

@@ -107,7 +107,7 @@ xdr_decode_fattr(u32 *p, struct nfs_fattr *fattr)
 	fattr->du.nfs2.blocksize = ntohl(*p++);
 	fattr->rdev = ntohl(*p++);
 	fattr->du.nfs2.blocks = ntohl(*p++);
-	fattr->fsid = ntohl(*p++);
+	fattr->fsid_u.nfs3 = ntohl(*p++);
 	fattr->fileid = ntohl(*p++);
 	p = xdr_decode_time(p, &fattr->atime);
 	p = xdr_decode_time(p, &fattr->mtime);

fs/nfs/nfs3proc.c

@@ -14,6 +14,7 @@
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
 #include <linux/smp_lock.h>
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
@@ -86,9 +87,10 @@ nfs3_proc_getattr(struct inode *inode, struct nfs_fattr *fattr)
 }
 
 static int
-nfs3_proc_setattr(struct inode *inode, struct nfs_fattr *fattr,
+nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 			struct iattr *sattr)
 {
+	struct inode *inode = dentry->d_inode;
 	struct nfs3_sattrargs	arg = {
 		.fh		= NFS_FH(inode),
 		.sattr		= sattr,
@@ -543,9 +545,10 @@ nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
  * readdirplus.
  */
 static int
-nfs3_proc_readdir(struct inode *dir, struct rpc_cred *cred,
+nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		  u64 cookie, struct page *page, unsigned int count, int plus)
 {
+	struct inode		*dir = dentry->d_inode;
 	struct nfs_fattr	dir_attr;
 	u32			*verf = NFS_COOKIEVERF(dir);
 	struct nfs3_readdirargs	arg = {
@@ -644,6 +647,51 @@ nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
 
 extern u32 *nfs3_decode_dirent(u32 *, struct nfs_entry *, int);
 
+static void
+nfs3_read_done(struct rpc_task *task)
+{
+	struct nfs_read_data *data = (struct nfs_read_data *) task->tk_calldata;
+
+	if (nfs_async_handle_jukebox(task))
+		return;
+	nfs_readpage_result(task, data->u.v3.res.count, data->u.v3.res.eof);
+}
+
+static void
+nfs3_proc_read_setup(struct nfs_read_data *data, unsigned int count)
+{
+	struct rpc_task		*task = &data->task;
+	struct inode		*inode = data->inode;
+	struct nfs_page		*req;
+	int			flags;
+	struct rpc_message	msg;
+	
+	req = nfs_list_entry(data->pages.next);
+	data->u.v3.args.fh     = NFS_FH(inode);
+	data->u.v3.args.offset = req_offset(req) + req->wb_offset;
+	data->u.v3.args.pgbase = req->wb_offset;
+	data->u.v3.args.pages  = data->pagevec;
+	data->u.v3.args.count  = count;
+	data->u.v3.res.fattr   = &data->fattr;
+	data->u.v3.res.count   = count;
+	data->u.v3.res.eof     = 0;
+	
+	/* N.B. Do we need to test? Never called for swapfile inode */
+	flags = RPC_TASK_ASYNC | (IS_SWAPFILE(inode)? NFS_RPC_SWAPFLAGS : 0);
+
+	/* Finalize the task. */
+	rpc_init_task(task, NFS_CLIENT(inode), nfs3_read_done, flags);
+	task->tk_calldata = data;
+	/* Release requests */
+	task->tk_release = nfs_readdata_release;
+
+	msg.rpc_proc = NFS3PROC_READ;
+	msg.rpc_argp = &data->u.v3.args;
+	msg.rpc_resp = &data->u.v3.res;
+	msg.rpc_cred = data->cred;
+	rpc_call_setup(&data->task, &msg, 0);
+}
+
 struct nfs_rpc_ops	nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.getroot	= nfs3_proc_get_root,
@@ -667,4 +715,5 @@ struct nfs_rpc_ops	nfs_v3_clientops = {
 	.mknod		= nfs3_proc_mknod,
 	.statfs		= nfs3_proc_statfs,
 	.decode_dirent	= nfs3_decode_dirent,
+	.read_setup	= nfs3_proc_read_setup,
 };

fs/nfs/nfs3xdr.c

@@ -173,7 +173,7 @@ xdr_decode_fattr(u32 *p, struct nfs_fattr *fattr)
 	/* Turn remote device info into Linux-specific dev_t */
 	fattr->rdev = ntohl(*p++) << MINORBITS;
 	fattr->rdev |= ntohl(*p++) & MINORMASK;
-	p = xdr_decode_hyper(p, &fattr->fsid);
+	p = xdr_decode_hyper(p, &fattr->fsid_u.nfs3);
 	p = xdr_decode_hyper(p, &fattr->fileid);
 	p = xdr_decode_time3(p, &fattr->atime);
 	p = xdr_decode_time3(p, &fattr->mtime);

fs/nfs/pagelist.c

@@ -14,6 +14,7 @@
 #include <linux/file.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs3.h>
+#include <linux/nfs4.h>
 #include <linux/nfs_page.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_flushd.h>
@@ -506,7 +507,7 @@ nfs_try_to_free_pages(struct nfs_server *server)
 			continue;
 		}
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 		/* Let's try to free up some completed NFSv3 unstable writes */
 		nfs_scan_lru_commit(server, &head);
 		if (!list_empty(&head)) {

fs/nfs/proc.c

@@ -41,6 +41,7 @@
 #include <linux/nfs.h>
 #include <linux/nfs2.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
 #include <linux/smp_lock.h>
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
@@ -78,9 +79,10 @@ nfs_proc_getattr(struct inode *inode, struct nfs_fattr *fattr)
 }
 
 static int
-nfs_proc_setattr(struct inode *inode, struct nfs_fattr *fattr,
+nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 		 struct iattr *sattr)
 {
+	struct inode *inode = dentry->d_inode;
 	struct nfs_sattrargs	arg = { 
 		.fh	= NFS_FH(inode),
 		.sattr	= sattr
@@ -425,9 +427,10 @@ nfs_proc_rmdir(struct inode *dir, struct qstr *name)
  * from nfs_readdir by calling the decode_entry function directly.
  */
 static int
-nfs_proc_readdir(struct inode *dir, struct rpc_cred *cred,
+nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		 u64 cookie, struct page *page, unsigned int count, int plus)
 {
+	struct inode		*dir = dentry->d_inode;
 	struct nfs_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
 		.cookie		= cookie,
@@ -467,6 +470,48 @@ nfs_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
 
 extern u32 * nfs_decode_dirent(u32 *, struct nfs_entry *, int);
 
+static void
+nfs_read_done(struct rpc_task *task)
+{
+	struct nfs_read_data *data = (struct nfs_read_data *) task->tk_calldata;
+	nfs_readpage_result(task, data->u.v3.res.count, data->u.v3.res.eof);
+}
+
+static void
+nfs_proc_read_setup(struct nfs_read_data *data, unsigned int count)
+{
+	struct rpc_task		*task = &data->task;
+	struct inode		*inode = data->inode;
+	struct nfs_page		*req;
+	int			flags;
+	struct rpc_message	msg;
+	
+	req = nfs_list_entry(data->pages.next);
+	data->u.v3.args.fh     = NFS_FH(inode);
+	data->u.v3.args.offset = req_offset(req) + req->wb_offset;
+	data->u.v3.args.pgbase = req->wb_offset;
+	data->u.v3.args.pages  = data->pagevec;
+	data->u.v3.args.count  = count;
+	data->u.v3.res.fattr   = &data->fattr;
+	data->u.v3.res.count   = count;
+	data->u.v3.res.eof     = 0;
+	
+	/* N.B. Do we need to test? Never called for swapfile inode */
+	flags = RPC_TASK_ASYNC | (IS_SWAPFILE(inode)? NFS_RPC_SWAPFLAGS : 0);
+
+	/* Finalize the task. */
+	rpc_init_task(task, NFS_CLIENT(inode), nfs_read_done, flags);
+	task->tk_calldata = data;
+	/* Release requests */
+	task->tk_release = nfs_readdata_release;
+
+	msg.rpc_proc = NFSPROC_READ;
+	msg.rpc_argp = &data->u.v3.args;
+	msg.rpc_resp = &data->u.v3.res;
+	msg.rpc_cred = data->cred;
+	rpc_call_setup(&data->task, &msg, 0);
+}
+
 struct nfs_rpc_ops	nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.getroot	= nfs_proc_get_root,
@@ -491,4 +536,5 @@ struct nfs_rpc_ops	nfs_v2_clientops = {
 	.mknod		= nfs_proc_mknod,
 	.statfs		= nfs_proc_statfs,
 	.decode_dirent	= nfs_decode_dirent,
+	.read_setup	= nfs_proc_read_setup,
 };

fs/nfs/read.c

@@ -34,27 +34,6 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
-struct nfs_read_data {
-	struct rpc_task		task;
-	struct inode		*inode;
-	struct rpc_cred		*cred;
-	struct nfs_readargs	args;	/* XDR argument struct */
-	struct nfs_readres	res;	/* ... and result struct */
-	struct nfs_fattr	fattr;	/* fattr storage */
-	struct list_head	pages;	/* Coalesced read requests */
-	struct page		*pagevec[NFS_READ_MAXIOV];
-};
-
-/*
- * Local function declarations
- */
-static void	nfs_readpage_result(struct rpc_task *task);
-
-/* Hack for future NFS swap support */
-#ifndef IS_SWAPFILE
-# define IS_SWAPFILE(inode)	(0)
-#endif
-
 static kmem_cache_t *nfs_rdata_cachep;
 
 static __inline__ struct nfs_read_data *nfs_readdata_alloc(void)
@@ -64,7 +43,6 @@ static __inline__ struct nfs_read_data *nfs_readdata_alloc(void)
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
-		p->args.pages = p->pagevec;
 	}
 	return p;
 }
@@ -74,7 +52,7 @@ static __inline__ void nfs_readdata_free(struct nfs_read_data *p)
 	kmem_cache_free(nfs_rdata_cachep, p);
 }
 
-static void nfs_readdata_release(struct rpc_task *task)
+void nfs_readdata_release(struct rpc_task *task)
 {
         struct nfs_read_data   *data = (struct nfs_read_data *)task->tk_calldata;
         nfs_readdata_free(data);
@@ -190,29 +168,32 @@ nfs_readpage_async(struct file *file, struct inode *inode, struct page *page)
 static void
 nfs_read_rpcsetup(struct list_head *head, struct nfs_read_data *data)
 {
+	struct inode		*inode;
 	struct nfs_page		*req;
 	struct page		**pages;
 	unsigned int		count;
 
-	pages = data->args.pages;
+	pages = data->pagevec;
 	count = 0;
 	while (!list_empty(head)) {
-		struct nfs_page *req = nfs_list_entry(head->next);
+		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
 		nfs_list_add_request(req, &data->pages);
 		*pages++ = req->wb_page;
 		count += req->wb_bytes;
 	}
 	req = nfs_list_entry(data->pages.next);
-	data->inode	  = req->wb_inode;
+	data->inode	  = inode = req->wb_inode;
 	data->cred	  = req->wb_cred;
-	data->args.fh     = NFS_FH(req->wb_inode);
-	data->args.offset = req_offset(req) + req->wb_offset;
-	data->args.pgbase = req->wb_offset;
-	data->args.count  = count;
-	data->res.fattr   = &data->fattr;
-	data->res.count   = count;
-	data->res.eof     = 0;
+
+	NFS_PROTO(inode)->read_setup(data, count);
+
+	dprintk("NFS: %4d initiated read call (req %s/%Ld, %u bytes @ offset %Lu.\n",
+			data->task.tk_pid,
+			inode->i_sb->s_id,
+			(long long)NFS_FILEID(inode),
+			count,
+			(unsigned long long)req_offset(req) + req->wb_offset);
 }
 
 static void
@@ -236,50 +217,20 @@ nfs_async_read_error(struct list_head *head)
 static int
 nfs_pagein_one(struct list_head *head, struct inode *inode)
 {
-	struct rpc_task		*task;
 	struct rpc_clnt		*clnt = NFS_CLIENT(inode);
 	struct nfs_read_data	*data;
-	struct rpc_message	msg;
-	int			flags;
 	sigset_t		oldset;
 
 	data = nfs_readdata_alloc();
 	if (!data)
 		goto out_bad;
-	task = &data->task;
-
-	/* N.B. Do we need to test? Never called for swapfile inode */
-	flags = RPC_TASK_ASYNC | (IS_SWAPFILE(inode)? NFS_RPC_SWAPFLAGS : 0);
 
 	nfs_read_rpcsetup(head, data);
 
-	/* Finalize the task. */
-	rpc_init_task(task, clnt, nfs_readpage_result, flags);
-	task->tk_calldata = data;
-	/* Release requests */
-	task->tk_release = nfs_readdata_release;
-
-#ifdef CONFIG_NFS_V3
-	msg.rpc_proc = (NFS_PROTO(inode)->version == 3) ? NFS3PROC_READ : NFSPROC_READ;
-#else
-	msg.rpc_proc = NFSPROC_READ;
-#endif
-	msg.rpc_argp = &data->args;
-	msg.rpc_resp = &data->res;
-	msg.rpc_cred = data->cred;
-
 	/* Start the async call */
-	dprintk("NFS: %4d initiated read call (req %s/%Ld, %u bytes @ offset %Lu.\n",
-		task->tk_pid,
-		inode->i_sb->s_id,
-		(long long)NFS_FILEID(inode),
-		(unsigned int)data->args.count,
-		(unsigned long long)data->args.offset);
-
 	rpc_clnt_sigmask(clnt, &oldset);
-	rpc_call_setup(task, &msg, 0);
 	lock_kernel();
-	rpc_execute(task);
+	rpc_execute(&data->task);
 	unlock_kernel();
 	rpc_clnt_sigunmask(clnt, &oldset);
 	return 0;
@@ -399,19 +350,15 @@ int nfs_pagein_inode(struct inode *inode, unsigned long idx_start,
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
  */
-static void
-nfs_readpage_result(struct rpc_task *task)
+void
+nfs_readpage_result(struct rpc_task *task, unsigned int count, int eof)
 {
 	struct nfs_read_data	*data = (struct nfs_read_data *) task->tk_calldata;
 	struct inode		*inode = data->inode;
-	unsigned int		count = data->res.count;
 
 	dprintk("NFS: %4d nfs_readpage_result, (status %d)\n",
 		task->tk_pid, task->tk_status);
 
-	if (nfs_async_handle_jukebox(task))
-		return;
-
 	nfs_refresh_inode(inode, &data->fattr);
 	while (!list_empty(&data->pages)) {
 		struct nfs_page *req = nfs_list_entry(data->pages.next);
@@ -424,7 +371,7 @@ nfs_readpage_result(struct rpc_task *task)
 				memset(p + count, 0, PAGE_CACHE_SIZE - count);
 				kunmap(page);
 				count = 0;
-				if (data->res.eof)
+				if (eof)
 					SetPageUptodate(page);
 				else
 					SetPageError(page);

fs/nfs/write.c

@@ -88,7 +88,7 @@ static struct nfs_page * nfs_update_request(struct file*, struct inode *,
 					    unsigned int, unsigned int);
 static void	nfs_strategy(struct inode *inode);
 static void	nfs_writeback_done(struct rpc_task *);
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 static void	nfs_commit_done(struct rpc_task *);
 #endif
 
@@ -414,7 +414,7 @@ nfs_dirty_request(struct nfs_page *req)
 	return !list_empty(&req->wb_list) && req->wb_list_head == &nfsi->dirty;
 }
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 /*
  * Add a request to the inode's commit list.
  */
@@ -552,7 +552,7 @@ nfs_scan_dirty(struct inode *inode, struct list_head *dst, struct file *file, un
 	return res;
 }
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 /**
  * nfs_scan_lru_commit_timeout - Scan LRU list for timed out commit requests
  * @server: NFS superblock data
@@ -747,7 +747,7 @@ nfs_strategy(struct inode *inode)
 
 	dirty  = NFS_I(inode)->ndirty;
 	wpages = NFS_SERVER(inode)->wpages;
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 	if (NFS_PROTO(inode)->version == 2) {
 		if (dirty >= NFS_STRATEGY_PAGES * wpages)
 			nfs_flush_file(inode, NULL, 0, 0, 0);
@@ -1032,7 +1032,7 @@ nfs_writeback_done(struct rpc_task *task)
 		 * an error. */
 		task->tk_status = -EIO;
 	}
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 	if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
 		 * commit data to stable storage even though we
@@ -1082,7 +1082,7 @@ nfs_writeback_done(struct rpc_task *task)
 			goto next;
 		}
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 		if (argp->stable != NFS_UNSTABLE || resp->verf->committed == NFS_FILE_SYNC) {
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
@@ -1101,7 +1101,7 @@ nfs_writeback_done(struct rpc_task *task)
 }
 
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 /*
  * Set up the argument/result storage required for the RPC call.
  */
@@ -1265,7 +1265,7 @@ int nfs_flush_file(struct inode *inode, struct file *file, unsigned long idx_sta
 	return res;
 }
 
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 int nfs_commit_file(struct inode *inode, struct file *file, unsigned long idx_start,
 		    unsigned int npages, int how)
 {
@@ -1302,7 +1302,7 @@ int nfs_sync_file(struct inode *inode, struct file *file, unsigned long idx_star
 			error = nfs_wait_on_requests(inode, file, idx_start, npages);
 		if (error == 0)
 			error = nfs_flush_file(inode, file, idx_start, npages, how);
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 		if (error == 0)
 			error = nfs_commit_file(inode, file, idx_start, npages, how);
 #endif

fs/proc/generic.c

@@ -165,6 +165,24 @@ proc_file_lseek(struct file * file, loff_t offset, int orig)
     return -EINVAL;
 }
 
+static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error = inode_setattr(inode, iattr);
+	if (!error) {
+		struct proc_dir_entry *de = PDE(inode);
+		de->uid = inode->i_uid;
+		de->gid = inode->i_gid;
+		de->mode = inode->i_mode;
+	}
+
+	return error;
+}
+
+static struct inode_operations proc_file_inode_operations = {
+	.setattr	= proc_notify_change,
+};
+
 /*
  * This function parses a name such as "tty/driver/serial", and
  * returns the struct proc_dir_entry for "/proc/tty/driver", and
@@ -368,6 +386,7 @@ static struct file_operations proc_dir_operations = {
  */
 static struct inode_operations proc_dir_inode_operations = {
 	.lookup		= proc_lookup,
+	.setattr	= proc_notify_change,
 };
 
 static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
@@ -393,6 +412,8 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 	} else if (S_ISREG(dp->mode)) {
 		if (dp->proc_fops == NULL)
 			dp->proc_fops = &proc_file_operations;
+		if (dp->proc_iops == NULL)
+			dp->proc_iops = &proc_file_inode_operations;
 	}
 	return 0;
 }

include/asm-i386/fixmap.h

@@ -65,6 +65,9 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_F00F_BUG
 	FIX_F00F_IDT,	/* Virtual mapping for IDT */
 #endif
+#ifdef CONFIG_X86_CYCLONE
+	FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif 
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,

include/asm-i386/timer.h

+#ifndef _ASMi386_TIMER_H
+#define _ASMi386_TIMER_H
+
+/**
+ * struct timer_ops - used to define a timer source
+ *
+ * @init: Probes and initializes the timer.  Returns 0 on success, anything
+ *	else on failure.
+ * @mark_offset: called by the timer interrupt
+ * @get_offset: called by gettimeofday().  Returns the number of ms since the
+ *	last timer intruupt.
+ */
+struct timer_opts{
+	int (*init)(void);
+	void (*mark_offset)(void);
+	unsigned long (*get_offset)(void);
+};
+
+#define TICK_SIZE (tick_nsec / 1000)
+
+extern struct timer_opts* select_timer(void);
+#endif

include/linux/nfs4.h

+/*
+ *  include/linux/nfs4.h
+ *
+ *  NFSv4 protocol definitions.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Kendrick Smith <kmsmith@umich.edu>
+ *  Andy Adamson   <andros@umich.edu>
+ */
+
+#ifndef _LINUX_NFS4_H
+#define _LINUX_NFS4_H
+
+#define NFS4_VERIFIER_SIZE	8
+#define NFS4_FHSIZE		128
+#define NFS4_MAXNAMLEN		NAME_MAX
+
+#define NFS4_ACCESS_READ        0x0001
+#define NFS4_ACCESS_LOOKUP      0x0002
+#define NFS4_ACCESS_MODIFY      0x0004
+#define NFS4_ACCESS_EXTEND      0x0008
+#define NFS4_ACCESS_DELETE      0x0010
+#define NFS4_ACCESS_EXECUTE     0x0020
+
+#define NFS4_FH_PERISTENT		0x0000
+#define NFS4_FH_NOEXPIRE_WITH_OPEN	0x0001
+#define NFS4_FH_VOLATILE_ANY		0x0002
+#define NFS4_FH_VOL_MIGRATION		0x0004
+#define NFS4_FH_VOL_RENAME		0x0008
+
+#define NFS4_OPEN_RESULT_CONFIRM 0x0002
+
+#define NFS4_SHARE_ACCESS_READ	0x0001
+#define NFS4_SHARE_ACCESS_WRITE	0x0002
+#define NFS4_SHARE_ACCESS_BOTH	0x0003
+
+#define NFS4_SET_TO_SERVER_TIME	0
+#define NFS4_SET_TO_CLIENT_TIME	1
+
+#define NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE 0
+#define NFS4_ACE_ACCESS_DENIED_ACE_TYPE  1
+#define NFS4_ACE_SYSTEM_AUDIT_ACE_TYPE   2
+#define NFS4_ACE_SYSTEM_ALARM_ACE_TYPE   3
+
+typedef char nfs4_verifier[NFS4_VERIFIER_SIZE];
+typedef char nfs4_stateid[16];
+
+enum nfs_opnum4 {
+	OP_ACCESS = 3,
+	OP_CLOSE = 4,
+	OP_COMMIT = 5,
+	OP_CREATE = 6,
+	OP_DELEGPURGE = 7,
+	OP_DELEGRETURN = 8,
+	OP_GETATTR = 9,
+	OP_GETFH = 10,
+	OP_LINK = 11,
+	OP_LOCK = 12,
+	OP_LOCKT = 13,
+	OP_LOCKU = 14,
+	OP_LOOKUP = 15,
+	OP_LOOKUPP = 16,
+	OP_NVERIFY = 17,
+	OP_OPEN = 18,
+	OP_OPENATTR = 19,
+	OP_OPEN_CONFIRM = 20,
+	OP_OPEN_DOWNGRADE = 21,
+	OP_PUTFH = 22,
+	OP_PUTPUBFH = 23,
+	OP_PUTROOTFH = 24,
+	OP_READ = 25,
+	OP_READDIR = 26,
+	OP_READLINK = 27,
+	OP_REMOVE = 28,
+	OP_RENAME = 29,
+	OP_RENEW = 30,
+	OP_RESTOREFH = 31,
+	OP_SAVEFH = 32,
+	OP_SECINFO = 33,
+	OP_SETATTR = 34,
+	OP_SETCLIENTID = 35,
+	OP_SETCLIENTID_CONFIRM = 36,
+	OP_VERIFY = 37,
+	OP_WRITE = 38,
+};
+
+/*
+ * Note: NF4BAD is not actually part of the protocol; it is just used
+ * internally by nfsd.
+ */
+enum nfs_ftype4 {
+	NF4BAD		= 0,
+        NF4REG          = 1,    /* Regular File */
+        NF4DIR          = 2,    /* Directory */
+        NF4BLK          = 3,    /* Special File - block device */
+        NF4CHR          = 4,    /* Special File - character device */
+        NF4LNK          = 5,    /* Symbolic Link */
+        NF4SOCK         = 6,    /* Special File - socket */
+        NF4FIFO         = 7,    /* Special File - fifo */
+        NF4ATTRDIR      = 8,    /* Attribute Directory */
+        NF4NAMEDATTR    = 9     /* Named Attribute */
+};
+
+enum open_claim_type4 {
+	NFS4_OPEN_CLAIM_NULL = 0,
+	NFS4_OPEN_CLAIM_PREVIOUS = 1,
+	NFS4_OPEN_CLAIM_DELEGATE_CUR = 2,
+	NFS4_OPEN_CLAIM_DELEGATE_PREV = 3
+};
+
+enum opentype4 {
+	NFS4_OPEN_NOCREATE = 0,
+	NFS4_OPEN_CREATE = 1
+};
+
+enum createmode4 {
+	NFS4_CREATE_UNCHECKED = 0,
+	NFS4_CREATE_GUARDED = 1,
+	NFS4_CREATE_EXCLUSIVE = 2
+};
+
+enum limit_by4 {
+	NFS4_LIMIT_SIZE = 1,
+	NFS4_LIMIT_BLOCKS = 2
+};
+
+enum open_delegation_type4 {
+	NFS4_OPEN_DELEGATE_NONE = 0,
+	NFS4_OPEN_DELEGATE_READ = 1,
+	NFS4_OPEN_DELEGATE_WRITE = 2
+};
+
+/* Mandatory Attributes */
+#define FATTR4_WORD0_SUPPORTED_ATTRS    (1)
+#define FATTR4_WORD0_TYPE               (1 << 1)
+#define FATTR4_WORD0_FH_EXPIRE_TYPE     (1 << 2)
+#define FATTR4_WORD0_CHANGE             (1 << 3)
+#define FATTR4_WORD0_SIZE               (1 << 4)
+#define FATTR4_WORD0_LINK_SUPPORT       (1 << 5)
+#define FATTR4_WORD0_SYMLINK_SUPPORT    (1 << 6)
+#define FATTR4_WORD0_NAMED_ATTR         (1 << 7)
+#define FATTR4_WORD0_FSID               (1 << 8)
+#define FATTR4_WORD0_UNIQUE_HANDLES     (1 << 9)
+#define FATTR4_WORD0_LEASE_TIME         (1 << 10)
+#define FATTR4_WORD0_RDATTR_ERROR       (1 << 11)
+
+/* Recommended Attributes */
+#define FATTR4_WORD0_ACL                (1 << 12)
+#define FATTR4_WORD0_ACLSUPPORT         (1 << 13)
+#define FATTR4_WORD0_ARCHIVE            (1 << 14)
+#define FATTR4_WORD0_CANSETTIME         (1 << 15)
+#define FATTR4_WORD0_CASE_INSENSITIVE   (1 << 16)
+#define FATTR4_WORD0_CASE_PRESERVING    (1 << 17)
+#define FATTR4_WORD0_CHOWN_RESTRICTED   (1 << 18)
+#define FATTR4_WORD0_FILEHANDLE         (1 << 19)
+#define FATTR4_WORD0_FILEID             (1 << 20)
+#define FATTR4_WORD0_FILES_AVAIL        (1 << 21)
+#define FATTR4_WORD0_FILES_FREE         (1 << 22)
+#define FATTR4_WORD0_FILES_TOTAL        (1 << 23)
+#define FATTR4_WORD0_FS_LOCATIONS       (1 << 24)
+#define FATTR4_WORD0_HIDDEN             (1 << 25)
+#define FATTR4_WORD0_HOMOGENEOUS        (1 << 26)
+#define FATTR4_WORD0_MAXFILESIZE        (1 << 27)
+#define FATTR4_WORD0_MAXLINK            (1 << 28)
+#define FATTR4_WORD0_MAXNAME            (1 << 29)
+#define FATTR4_WORD0_MAXREAD            (1 << 30)
+#define FATTR4_WORD0_MAXWRITE           (1 << 31)
+#define FATTR4_WORD1_MIMETYPE           (1)
+#define FATTR4_WORD1_MODE               (1 << 1)
+#define FATTR4_WORD1_NO_TRUNC           (1 << 2)
+#define FATTR4_WORD1_NUMLINKS           (1 << 3)
+#define FATTR4_WORD1_OWNER              (1 << 4)
+#define FATTR4_WORD1_OWNER_GROUP        (1 << 5)
+#define FATTR4_WORD1_QUOTA_HARD         (1 << 6)
+#define FATTR4_WORD1_QUOTA_SOFT         (1 << 7)
+#define FATTR4_WORD1_QUOTA_USED         (1 << 8)
+#define FATTR4_WORD1_RAWDEV             (1 << 9)
+#define FATTR4_WORD1_SPACE_AVAIL        (1 << 10)
+#define FATTR4_WORD1_SPACE_FREE         (1 << 11)
+#define FATTR4_WORD1_SPACE_TOTAL        (1 << 12)
+#define FATTR4_WORD1_SPACE_USED         (1 << 13)
+#define FATTR4_WORD1_SYSTEM             (1 << 14)
+#define FATTR4_WORD1_TIME_ACCESS        (1 << 15)
+#define FATTR4_WORD1_TIME_ACCESS_SET    (1 << 16)
+#define FATTR4_WORD1_TIME_BACKUP        (1 << 17)
+#define FATTR4_WORD1_TIME_CREATE        (1 << 18)
+#define FATTR4_WORD1_TIME_DELTA         (1 << 19)
+#define FATTR4_WORD1_TIME_METADATA      (1 << 20)
+#define FATTR4_WORD1_TIME_MODIFY        (1 << 21)
+#define FATTR4_WORD1_TIME_MODIFY_SET    (1 << 22)
+
+#define NFSPROC4_NULL 0
+#define NFSPROC4_COMPOUND 1
+#define NFS4_MINOR_VERSION 0
+#define NFS4_DEBUG 1
+
+#endif
+
+/*
+ * Local variables:
+ *  c-basic-offset: 8
+ * End:
+ */

include/linux/nfs_fs.h

@@ -25,6 +25,7 @@
 #include <linux/nfs.h>
 #include <linux/nfs2.h>
 #include <linux/nfs3.h>
+#include <linux/nfs4.h>
 #include <linux/nfs_page.h>
 #include <linux/nfs_xdr.h>
 
@@ -143,6 +144,7 @@ struct nfs_inode {
 	__u64			read_cache_isize;
 	unsigned long		attrtimeo;
 	unsigned long		attrtimeo_timestamp;
+	__u64			change_attr;		/* v4 only */
 
 	/*
 	 * Timestamp that dates the change made to read_cache_mtime.
@@ -207,6 +209,7 @@ static inline struct nfs_inode *NFS_I(struct inode *inode)
 #define NFS_CACHE_CTIME(inode)		(NFS_I(inode)->read_cache_ctime)
 #define NFS_CACHE_MTIME(inode)		(NFS_I(inode)->read_cache_mtime)
 #define NFS_CACHE_ISIZE(inode)		(NFS_I(inode)->read_cache_isize)
+#define NFS_CHANGE_ATTR(inode)		(NFS_I(inode)->change_attr)
 #define NFS_NEXTSCAN(inode)		(NFS_I(inode)->nextscan)
 #define NFS_CACHEINV(inode) \
 do { \
@@ -329,7 +332,7 @@ extern int  nfs_flush_file(struct inode *, struct file *, unsigned long, unsigne
 extern int  nfs_flush_list(struct list_head *, int, int);
 extern int  nfs_scan_lru_dirty(struct nfs_server *, struct list_head *);
 extern int  nfs_scan_lru_dirty_timeout(struct nfs_server *, struct list_head *);
-#ifdef CONFIG_NFS_V3
+#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 extern int  nfs_commit_file(struct inode *, struct file *, unsigned long, unsigned int, int);
 extern int  nfs_commit_list(struct list_head *, int);
 extern int  nfs_scan_lru_commit(struct nfs_server *, struct list_head *);
@@ -376,6 +379,11 @@ nfs_wb_file(struct inode *inode, struct file *file)
 	return (error < 0) ? error : 0;
 }
 
+/* Hack for future NFS swap support */
+#ifndef IS_SWAPFILE
+# define IS_SWAPFILE(inode)	(0)
+#endif
+
 /*
  * linux/fs/nfs/read.c
  */
@@ -384,6 +392,8 @@ extern int  nfs_pagein_inode(struct inode *, unsigned long, unsigned int);
 extern int  nfs_pagein_list(struct list_head *, int);
 extern int  nfs_scan_lru_read(struct nfs_server *, struct list_head *);
 extern int  nfs_scan_lru_read_timeout(struct nfs_server *, struct list_head *);
+extern void nfs_readpage_result(struct rpc_task *, unsigned int count, int eof);
+extern void nfs_readdata_release(struct rpc_task *);
 
 /*
  * linux/fs/mount_clnt.c

include/linux/nfs_xdr.h

@@ -24,17 +24,27 @@ struct nfs_fattr {
 		} nfs3;
 	} du;
 	__u32			rdev;
-	__u64			fsid;
+	union {
+		__u64		nfs3;		/* also nfs2 */
+		struct {
+			__u64	major;
+			__u64	minor;
+		} nfs4;
+	} fsid_u;
 	__u64			fileid;
 	__u64			atime;
 	__u64			mtime;
 	__u64			ctime;
+	__u64			change_attr;	/* NFSv4 change attribute */
+	__u64			pre_change_attr;/* pre-op NFSv4 change attribute */
 	unsigned long		timestamp;
 };
 
 #define NFS_ATTR_WCC		0x0001		/* pre-op WCC data    */
 #define NFS_ATTR_FATTR		0x0002		/* post-op attributes */
 #define NFS_ATTR_FATTR_V3	0x0004		/* NFSv3 attributes */
+#define NFS_ATTR_FATTR_V4	0x0008
+#define NFS_ATTR_PRE_CHANGE	0x0010
 
 /*
  * Info on the file system
@@ -298,6 +308,24 @@ struct nfs3_readdirres {
 	int			plus;
 };
 
+struct nfs_read_data {
+	struct rpc_task		task;
+	struct inode		*inode;
+	struct rpc_cred		*cred;
+	struct nfs_fattr	fattr;	/* fattr storage */
+	struct list_head	pages;	/* Coalesced read requests */
+	struct page		*pagevec[NFS_READ_MAXIOV];
+	union {
+		struct {
+			struct nfs_readargs args;
+			struct nfs_readres  res;
+		} v3;   /* also v2 */
+#ifdef CONFIG_NFS_V4
+		/* NFSv4 data will come here... */
+#endif
+	} u;
+};
+
 /*
  * RPC procedure vector for NFSv2/NFSv3 demuxing
  */
@@ -307,7 +335,7 @@ struct nfs_rpc_ops {
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fattr *);
 	int	(*getattr) (struct inode *, struct nfs_fattr *);
-	int	(*setattr) (struct inode *, struct nfs_fattr *,
+	int	(*setattr) (struct dentry *, struct nfs_fattr *,
 			    struct iattr *);
 	int	(*lookup)  (struct inode *, struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
@@ -338,13 +366,14 @@ struct nfs_rpc_ops {
 	int	(*mkdir)   (struct inode *, struct qstr *, struct iattr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 	int	(*rmdir)   (struct inode *, struct qstr *);
-	int	(*readdir) (struct inode *, struct rpc_cred *,
+	int	(*readdir) (struct dentry *, struct rpc_cred *,
 			    u64, struct page *, unsigned int, int);
 	int	(*mknod)   (struct inode *, struct qstr *, struct iattr *,
 			    dev_t, struct nfs_fh *, struct nfs_fattr *);
 	int	(*statfs)  (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
 	u32 *	(*decode_dirent)(u32 *, struct nfs_entry *, int plus);
+	void	(*read_setup)   (struct nfs_read_data *, unsigned int count);
 };
 
 /*

include/linux/nfsd/const.h

@@ -12,6 +12,7 @@
 #include <linux/nfs.h>
 #include <linux/nfs2.h>
 #include <linux/nfs3.h>
+#include <linux/nfs4.h>
 
 /*
  * Maximum protocol version supported by knfsd

include/linux/pci_ids.h

@@ -623,6 +623,7 @@
 #define PCI_VENDOR_ID_MOTOROLA_OOPS	0x1507
 #define PCI_DEVICE_ID_MOTOROLA_MPC105	0x0001
 #define PCI_DEVICE_ID_MOTOROLA_MPC106	0x0002
+#define PCI_DEVICE_ID_MOTOROLA_MPC107	0x0004
 #define PCI_DEVICE_ID_MOTOROLA_RAVEN	0x4801
 #define PCI_DEVICE_ID_MOTOROLA_FALCON	0x4802
 #define PCI_DEVICE_ID_MOTOROLA_HAWK	0x4803

include/linux/sunrpc/xprt.h

@@ -146,6 +146,7 @@ struct rpc_xprt {
 	unsigned long		sockstate;	/* Socket state */
 	unsigned char		shutdown   : 1,	/* being shut down */
 				nocong	   : 1,	/* no congestion control */
+				resvport   : 1, /* use a reserved port */
 				stream     : 1;	/* TCP */
 
 	/*

init/Makefile

@@ -17,4 +17,4 @@ $(obj)/version.o: $(objtree)/include/linux/compile.h
 
 $(objtree)/include/linux/compile.h: FORCE
 	@echo -n '  Generating $@'
-	@$(srctree)/scripts/mkcompile_h $@ "$(ARCH)" "$(CONFIG_SMP)" "$(CC) $(CFLAGS)"
+	@sh $(srctree)/scripts/mkcompile_h $@ "$(ARCH)" "$(CONFIG_SMP)" "$(CC) $(CFLAGS)"

kernel/sysctl.c

@@ -88,8 +88,8 @@ extern int sysctl_ieee_emulation_warnings;
 extern int sysctl_userprocess_debug;
 #endif
 
-#ifdef CONFIG_PPC32
-extern unsigned long zero_paged_on, powersave_nap;
+#if defined(CONFIG_PPC32) && defined(CONFIG_6xx)
+extern unsigned long powersave_nap;
 int proc_dol2crvec(ctl_table *table, int write, struct file *filp,
 		  void *buffer, size_t *lenp);
 #endif
@@ -190,9 +190,7 @@ static ctl_table kern_table[] = {
 	{KERN_SPARC_STOP_A, "stop-a", &stop_a_enabled, sizeof (int),
 	 0644, NULL, &proc_dointvec},
 #endif
-#ifdef CONFIG_PPC32
-	{KERN_PPC_ZEROPAGED, "zero-paged", &zero_paged_on, sizeof(int),
-	 0644, NULL, &proc_dointvec},
+#if defined(CONFIG_PPC32) && defined(CONFIG_6xx)
 	{KERN_PPC_POWERSAVE_NAP, "powersave-nap", &powersave_nap, sizeof(int),
 	 0644, NULL, &proc_dointvec},
 	{KERN_PPC_L2CR, "l2cr", NULL, 0,

net/sunrpc/xprt.c

@@ -89,7 +89,7 @@ static void	xprt_disconnect(struct rpc_xprt *);
 static void	xprt_conn_status(struct rpc_task *task);
 static struct rpc_xprt * xprt_setup(int proto, struct sockaddr_in *ap,
 						struct rpc_timeout *to);
-static struct socket *xprt_create_socket(int, struct rpc_timeout *);
+static struct socket *xprt_create_socket(int, struct rpc_timeout *, int);
 static void	xprt_bind_socket(struct rpc_xprt *, struct socket *);
 static int      __xprt_get_cong(struct rpc_xprt *, struct rpc_task *);
 
@@ -442,7 +442,7 @@ xprt_connect(struct rpc_task *task)
 	 * Start by resetting any existing state.
 	 */
 	xprt_close(xprt);
-	if (!(sock = xprt_create_socket(xprt->prot, &xprt->timeout))) {
+	if (!(sock = xprt_create_socket(xprt->prot, &xprt->timeout, xprt->resvport))) {
 		/* couldn't create socket or bind to reserved port;
 		 * this is likely a permanent error, so cause an abort */
 		task->tk_status = -EIO;
@@ -1490,7 +1490,7 @@ xprt_sock_setbufsize(struct rpc_xprt *xprt)
  * and connect stream sockets.
  */
 static struct socket *
-xprt_create_socket(int proto, struct rpc_timeout *to)
+xprt_create_socket(int proto, struct rpc_timeout *to, int resvport)
 {
 	struct socket	*sock;
 	int		type, err;
@@ -1506,7 +1506,7 @@ xprt_create_socket(int proto, struct rpc_timeout *to)
 	}
 
 	/* If the caller has the capability, bind to a reserved port */
-	if (capable(CAP_NET_BIND_SERVICE) && xprt_bindresvport(sock) < 0) {
+	if (resvport && xprt_bindresvport(sock) < 0) {
 		printk("RPC: can't bind to reserved port.\n");
 		goto failed;
 	}
@@ -1528,29 +1528,25 @@ xprt_create_proto(int proto, struct sockaddr_in *sap, struct rpc_timeout *to)
 
 	xprt = xprt_setup(proto, sap, to);
 	if (!xprt)
-		goto out;
+		goto out_bad;
 
+	xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0;
 	if (!xprt->stream) {
-		struct socket *sock = xprt_create_socket(proto, to);
-		if (sock)
+		struct socket *sock;
+
+		sock = xprt_create_socket(proto, to, xprt->resvport);
+		if (!sock)
+			goto out_bad;
 		xprt_bind_socket(xprt, sock);
-		else {
-			rpc_free(xprt);
-			xprt = NULL;
-		}
-	} else
-		/*
-		 * Don't allow a TCP service user unless they have
-		 * enough capability to bind a reserved port.
-		 */
-		if (!capable(CAP_NET_BIND_SERVICE)) {
-			rpc_free(xprt);
-			xprt = NULL;
 	}
 
- out:
 	dprintk("RPC:      xprt_create_proto created xprt %p\n", xprt);
 	return xprt;
+ out_bad:
+	dprintk("RPC:      xprt_create_proto failed\n");
+	if (xprt)
+		rpc_free(xprt);
+	return NULL;
 }
 
 /*

scripts/fixdep.c

@@ -61,7 +61,7 @@
  *
  * It is invoked as
  *
- *   fixdep <depfile> <target> <topdir> <cmdline>
+ *   fixdep <depfile> <target> <cmdline>
  *
  * and will read the dependency file <depfile>
  *
@@ -111,7 +111,6 @@
 #define INT_NFIG ntohl(0x4e464947)
 #define INT_FIG_ ntohl(0x4649475f)
 
-char *topdir;
 char *target;
 char *depfile;
 char *cmdline;
@@ -119,7 +118,7 @@ char *cmdline;
 void usage(void)
 
 {
-	fprintf(stderr, "Usage: fixdep <depfile> <target> <topdir> <cmdline>\n");
+	fprintf(stderr, "Usage: fixdep <depfile> <target> <cmdline>\n");
 	exit(1);
 }
 
@@ -364,13 +363,12 @@ int main(int argc, char *argv[])
 {
 	traps();
 
-	if (argc != 5)
+	if (argc != 4)
 		usage();
 		
 	depfile = argv[1];
 	target = argv[2];
-	topdir = argv[3];
-	cmdline = argv[4];
+	cmdline = argv[3];
 
 	print_cmdline();
 	print_deps();