Merge

arch/alpha/Config.help

@@ -251,6 +251,10 @@ CONFIG_ALPHA_PRIMO
 CONFIG_ALPHA_GAMMA
   Say Y if you have an AS 2000 5/xxx or an AS 2100 5/xxx.
 
+CONFIG_ALPHA_EV67
+  Is this a machine based on the EV67 core?  If in doubt, select N here
+  and the machine will be treated as an EV6.
+
 CONFIG_ALPHA_SRM
   There are two different types of booting firmware on Alphas: SRM,
   which is command line driven, and ARC, which uses menus and arrow
@@ -610,3 +614,14 @@ CONFIG_DEBUG_SPINLOCK
   best used in conjunction with the NMI watchdog so that spinlock
   deadlocks are also debuggable.
 
+CONFIG_DEBUG_RWLOCK
+  If you say Y here then read-write lock processing will count how many
+  times it has tried to get the lock and issue an error message after
+  too many attempts.  If you suspect a rwlock problem or a kernel
+  hacker asks for this option then say Y.  Otherwise say N.
+
+CONFIG_DEBUG_SEMAPHORE
+  If you say Y here then semaphore processing will issue lots of
+  verbose debugging messages.  If you suspect a semaphore problem or a
+  kernel hacker asks for this option then say Y.  Otherwise say N.
+

arch/alpha/Makefile

@@ -99,30 +99,32 @@ export libs-y
 
 MAKEBOOT = $(MAKE) -C arch/alpha/boot
 
-rawboot:
+rawboot:	vmlinux
 	@$(MAKEBOOT) rawboot
 
+boot:	vmlinux
+	@$(MAKEBOOT)
+
 #
 # My boot writes directly to a specific disk partition, I doubt most
 # people will want to do that without changes..
 #
-msb my-special-boot:
+msb my-special-boot:	vmlinux
 	@$(MAKEBOOT) msb
 
-bootimage:
+bootimage:	vmlinux
 	@$(MAKEBOOT) bootimage
 
-srmboot:
+srmboot:	vmlinux
 	@$(MAKEBOOT) srmboot
 
 archclean:
-	@$(MAKE) -C arch/alpha/kernel clean
 	@$(MAKEBOOT) clean
 
 archmrproper:
 	rm -f include/asm-alpha/asm_offsets.h
 
-bootpfile:
+bootpfile:	vmlinux
 	@$(MAKEBOOT) bootpfile
 
 

arch/alpha/boot/Makefile

@@ -8,7 +8,9 @@
 # Copyright (C) 1994 by Linus Torvalds
 #
 
-LINKFLAGS = -static -T bootloader.lds #-N -relax
+LINKFLAGS = -static -T bootloader.lds -uvsprintf #-N -relax
+
+CFLAGS := $(CFLAGS) -I$(TOPDIR)/include
 
 .S.s:
 	$(CPP) $(AFLAGS) -traditional -o $*.o $<

arch/alpha/kernel/Makefile

@@ -8,8 +8,9 @@ EXTRA_AFLAGS	:= $(CFLAGS)
 
 export-objs := alpha_ksyms.o
 
-obj-y    := entry.o traps.o process.o init_task.o osf_sys.o irq.o irq_alpha.o \
-	    signal.o setup.o ptrace.o time.o semaphore.o alpha_ksyms.o
+obj-y    := entry.o traps.o process.o init_task.o osf_sys.o irq.o \
+	    irq_alpha.o signal.o setup.o ptrace.o time.o semaphore.o \
+	    alpha_ksyms.o systbls.o
 
 #
 # FIXME!

arch/alpha/kernel/alpha_ksyms.c

@@ -161,7 +161,6 @@ EXPORT_SYMBOL(sys_read);
 EXPORT_SYMBOL(sys_lseek);
 EXPORT_SYMBOL(__kernel_execve);
 EXPORT_SYMBOL(sys_setsid);
-EXPORT_SYMBOL(sys_sync);
 EXPORT_SYMBOL(sys_wait4);
 
 /* Networking helper routines. */

arch/alpha/kernel/process.c

@@ -191,26 +191,13 @@ machine_power_off(void)
 	common_shutdown(LINUX_REBOOT_CMD_POWER_OFF, NULL);
 }
 
+/* Used by sysrq-p, among others.  I don't believe r9-r15 are ever
+   saved in the context it's used.  */
+
 void
-show_regs(struct pt_regs * regs)
+show_regs(struct pt_regs *regs)
 {
-	printk("\n");
-	printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
-	printk("ps: %04lx pc: [<%016lx>] CPU %d    %s\n",
-	       regs->ps, regs->pc, smp_processor_id(), print_tainted());
-	printk("rp: [<%016lx>] sp: %p\n", regs->r26, regs+1);
-	printk(" r0: %016lx  r1: %016lx  r2: %016lx  r3: %016lx\n",
-	       regs->r0, regs->r1, regs->r2, regs->r3);
-	printk(" r4: %016lx  r5: %016lx  r6: %016lx  r7: %016lx\n",
-	       regs->r4, regs->r5, regs->r6, regs->r7);
-	printk(" r8: %016lx r16: %016lx r17: %016lx r18: %016lx\n",
-	       regs->r8, regs->r16, regs->r17, regs->r18);
-	printk("r19: %016lx r20: %016lx r21: %016lx r22: %016lx\n",
-	       regs->r19, regs->r20, regs->r21, regs->r22);
-	printk("r23: %016lx r24: %016lx r25: %016lx r26: %016lx\n",
-	       regs->r23, regs->r24, regs->r25, regs->r26);
-	printk("r27: %016lx r28: %016lx r29: %016lx hae: %016lx\n",
-	       regs->r27, regs->r28, regs->gp, regs->hae);
+	dik_show_regs(regs, 0);
 }
 
 /*

arch/alpha/kernel/setup.c

@@ -37,6 +37,11 @@
 #include <linux/blk.h>
 #endif
 
+#ifdef CONFIG_MAGIC_SYSRQ
+#include <linux/sysrq.h>
+#include <linux/reboot.h>
+#endif
+
 #include <linux/notifier.h>
 extern struct notifier_block *panic_notifier_list;
 static int alpha_panic_event(struct notifier_block *, unsigned long, void *);
@@ -539,6 +544,15 @@ setup_arch(char **cmdline_p)
 		register_srm_console();
 	}
 
+#ifdef CONFIG_MAGIC_SYSRQ
+	/* If we're using SRM, make sysrq-b halt back to the prom,
+	   not auto-reboot.  */
+	if (alpha_using_srm) {
+		struct sysrq_key_op *op = __sysrq_get_key_op('b');
+		op->handler = (void *) machine_halt;
+	}
+#endif
+
 	/*
 	 * Indentify and reconfigure for the current system.
 	 */

arch/alpha/lib/Makefile

@@ -51,14 +51,16 @@ obj-$(CONFIG_SMP) += dec_and_lock.o
 
 include $(TOPDIR)/Rules.make
 
-__divqu.o: $(ev6)divide.S
-	$(CC) $(AFLAGS) -DDIV -c -o __divqu.o $(ev6)divide.S
+$(obj)/__divqu.o: $(obj)/$(ev6)divide.S
+	$(CC) $(AFLAGS) -DDIV -c -o $(obj)/__divqu.o $(obj)/$(ev6)divide.S
 
-__remqu.o: $(ev6)divide.S
-	$(CC) $(AFLAGS) -DREM -c -o __remqu.o $(ev6)divide.S
+$(obj)/__remqu.o: $(obj)/$(ev6)divide.S
+	$(CC) $(AFLAGS) -DREM -c -o $(obj)/__remqu.o $(obj)/$(ev6)divide.S
 
-__divlu.o: $(ev6)divide.S
-	$(CC) $(AFLAGS) -DDIV -DINTSIZE -c -o __divlu.o $(ev6)divide.S
+$(obj)/__divlu.o: $(obj)/$(ev6)divide.S
+	$(CC) $(AFLAGS) -DDIV -DINTSIZE \
+		-c -o $(obj)/__divlu.o $(obj)/$(ev6)divide.S
 
-__remlu.o: $(ev6)divide.S
-	$(CC) $(AFLAGS) -DREM -DINTSIZE -c -o __remlu.o $(ev6)divide.S
+$(obj)/__remlu.o: $(obj)/$(ev6)divide.S
+	$(CC) $(AFLAGS) -DREM -DINTSIZE \
+		-c -o $(obj)/__remlu.o $(obj)/$(ev6)divide.S

arch/alpha/lib/stxncpy.S

@@ -278,7 +278,7 @@ $u_eoc:
 	extqh	t2, a1, t0	# e0    : extract low bits for last word
 	or	t1, t0, t1	# e1    :
 
-1:	cmpbge	zero, t1, t7
+1:	cmpbge	zero, t1, t8
 	mov	t1, t0
 
 $u_eocfin:			# end-of-count, final word

arch/alpha/mm/fault.c

@@ -125,11 +125,10 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		goto bad_area;
 	if (expand_stack(vma, address))
 		goto bad_area;
-/*
- * Ok, we have a good vm_area for this memory access, so
- * we can handle it..
- */
-good_area:
+
+	/* Ok, we have a good vm_area for this memory access, so
+	   we can handle it.  */
+ good_area:
 	if (cause < 0) {
 		if (!(vma->vm_flags & VM_EXEC))
 			goto bad_area;
@@ -143,11 +142,9 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	}
 
  survive:
-	/*
-	 * If for any reason at all we couldn't handle the fault,
-	 * make sure we exit gracefully rather than endlessly redo
-	 * the fault.
-	 */
+	/* If for any reason at all we couldn't handle the fault,
+	   make sure we exit gracefully rather than endlessly redo
+	   the fault.  */
 	fault = handle_mm_fault(mm, vma, address, cause > 0);
 	up_read(&mm->mmap_sem);
 
@@ -155,14 +152,11 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		goto out_of_memory;
 	if (fault == 0)
 		goto do_sigbus;
-
 	return;
 
-/*
- * Something tried to access memory that isn't in our memory map..
- * Fix it, but check if it's kernel or user first..
- */
-bad_area:
+	/* Something tried to access memory that isn't in our memory map.
+	   Fix it, but check if it's kernel or user first.  */
+ bad_area:
 	up_read(&mm->mmap_sem);
 
 	if (user_mode(regs)) {
@@ -170,7 +164,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		return;
 	}
 
-no_context:
+ no_context:
 	/* Are we prepared to handle this fault as an exception?  */
 	if ((fixup = search_exception_table(regs->pc, regs->gp)) != 0) {
 		unsigned long newpc;
@@ -183,20 +177,16 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		return;
 	}
 
-/*
- * Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
- */
+	/* Oops. The kernel tried to access some bad page. We'll have to
+	   terminate things with extreme prejudice.  */
 	printk(KERN_ALERT "Unable to handle kernel paging request at "
 	       "virtual address %016lx\n", address);
 	die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16);
 	do_exit(SIGKILL);
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
-out_of_memory:
+	/* We ran out of memory, or some other thing happened to us that
+	   made us unable to handle the page fault gracefully.  */
+ out_of_memory:
 	if (current->pid == 1) {
 		yield();
 		down_read(&mm->mmap_sem);
@@ -208,18 +198,16 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 		goto no_context;
 	do_exit(SIGKILL);
 
-do_sigbus:
-	/*
-	 * Send a sigbus, regardless of whether we were in kernel
-	 * or user mode.
-	 */
+ do_sigbus:
+	/* Send a sigbus, regardless of whether we were in kernel
+	   or user mode.  */
 	force_sig(SIGBUS, current);
 	if (!user_mode(regs))
 		goto no_context;
 	return;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
-vmalloc_fault:
+ vmalloc_fault:
 	if (user_mode(regs)) {
 		force_sig(SIGSEGV, current);
 		return;

arch/alpha/vmlinux.lds.S

@@ -58,10 +58,11 @@ SECTIONS
 	__initcall_end = .;
   }
 
-  . = ALIGN(64);
-  __per_cpu_start = .;
-  .data.percpu  : { *(.data.percpu) }
-  __per_cpu_end = .;
+  .data.percpu ALIGN(64): {
+	__per_cpu_start = .;
+	*(.data.percpu)
+	__per_cpu_end = .;
+  }
 
   /* The initial task and kernel stack */
   .data.init_thread ALIGN(2*8192) : {

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

@@ -53,7 +53,7 @@ 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/ \
-					   arch/i386/$(MACHINE)/
+					   arch/i386/$(MACHINE)/ arch/i386/kernel/timers/
 drivers-$(CONFIG_MATH_EMULATION)	+= arch/i386/math-emu/
 drivers-$(CONFIG_PCI)			+= arch/i386/pci/
 

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

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 1;
+}
+
+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 <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 1;
+		}
+	}
+	return 0;
+}
+
+/************************************************************/
+
+/* tsc timer_opts struct */
+struct timer_opts timer_tsc = {
+	init: init_tsc, 
+	mark_offset: mark_offset_tsc, 
+	get_offset: get_offset_tsc
+};

drivers/char/raw.c

@@ -30,6 +30,10 @@ static struct file_operations raw_ctl_fops;
 /*
  * Open/close code for raw IO.
  *
+ * We just rewrite the i_mapping for the /dev/raw/rawN file descriptor to
+ * point at the blockdev's address_space and set the file handle to use
+ * O_DIRECT.
+ *
  * Set the device's soft blocksize to the minimum possible.  This gives the
  * finest possible alignment and has no adverse impact on performance.
  */
@@ -56,7 +60,12 @@ static int raw_open(struct inode *inode, struct file *filp)
 		err = blkdev_get(bdev, filp->f_mode, 0, BDEV_RAW);
 		if (!err) {
 			err = set_blocksize(bdev, bdev_hardsect_size(bdev));
-			raw_devices[minor].inuse++;
+			if (err == 0) {
+				raw_devices[minor].inuse++;
+				filp->f_dentry->d_inode->i_mapping =
+					bdev->bd_inode->i_mapping;
+				filp->f_flags |= O_DIRECT;
+			}
 		}
 	}
 	up(&raw_mutex);
@@ -200,72 +209,22 @@ raw_ctl_ioctl(struct inode *inode, struct file *filp,
 	return err;
 }
 
-static ssize_t
-rw_raw_dev(int rw, struct file *filp, const struct iovec *iov, unsigned long nr_segs, loff_t *offp)
-{
-	const int minor = minor(filp->f_dentry->d_inode->i_rdev);
-	struct block_device *bdev = raw_devices[minor].binding;
-	struct inode *inode = bdev->bd_inode;
- 	size_t count = iov_length(iov, nr_segs); 
-	ssize_t ret = 0;
-
-	if (count == 0)
-		goto out;	
-
-	if ((ssize_t)count < 0)
-		return -EINVAL;	
-
-	if (*offp >= inode->i_size) 
-		return -ENXIO;
-
-	if (count + *offp > inode->i_size) {
-		count = inode->i_size - *offp;
-		nr_segs = iov_shorten((struct iovec *)iov, nr_segs, count);
-	}
-	ret = generic_file_direct_IO(rw, filp, iov, *offp, nr_segs);
-
-	if (ret > 0)
-		*offp += ret;
-out:
-	return ret;
-}
-
-static ssize_t
-raw_read(struct file *filp, char *buf, size_t size, loff_t *offp)
-{
-	struct iovec local_iov = { .iov_base = buf, .iov_len = size};
-
-	return rw_raw_dev(READ, filp, &local_iov, 1, offp);
-}
-
-static ssize_t
-raw_write(struct file *filp, const char *buf, size_t size, loff_t *offp)
+static ssize_t raw_file_write(struct file *file, const char *buf,
+				   size_t count, loff_t *ppos)
 {
-	struct iovec local_iov = { .iov_base = (char *)buf, .iov_len = size};
+	struct iovec local_iov = { .iov_base = (void *)buf, .iov_len = count };
 
-	return rw_raw_dev(WRITE, filp, &local_iov, 1, offp);
-}
-
-static ssize_t 
-raw_readv(struct file *filp, const struct iovec *iov, unsigned long nr_segs, loff_t *offp) 
-{
-	return rw_raw_dev(READ, filp, iov, nr_segs, offp);
-}
-
-static ssize_t 
-raw_writev(struct file *filp, const struct iovec *iov, unsigned long nr_segs, loff_t *offp) 
-{
-	return rw_raw_dev(WRITE, filp, iov, nr_segs, offp);
+	return generic_file_write_nolock(file, &local_iov, 1, ppos);
 }
 
 static struct file_operations raw_fops = {
-	.read	=	raw_read,
-	.write	=	raw_write,
+	.read	=	generic_file_read,
+	.write	=	raw_file_write,
 	.open	=	raw_open,
 	.release=	raw_release,
 	.ioctl	=	raw_ioctl,
-	.readv	= 	raw_readv,
-	.writev	= 	raw_writev,
+	.readv	= 	generic_file_readv,
+	.writev	= 	generic_file_writev,
 	.owner	=	THIS_MODULE,
 };
 

fs/jbd/transaction.c

@@ -1434,9 +1434,10 @@ int journal_stop(handle_t *handle)
 	 * by 30x or more...
 	 */
 	if (handle->h_sync) {
+		set_current_state(TASK_RUNNING);
 		do {
 			old_handle_count = transaction->t_handle_count;
-			yield();
+			schedule();
 		} while (old_handle_count != transaction->t_handle_count);
 	}
 

fs/read_write.c

@@ -316,7 +316,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov=iovstack;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
 	int seg;
 	io_fn_t fn;
 	iov_fn_t fnv;
@@ -325,8 +325,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	/*
 	 * SuS says "The readv() function *may* fail if the iovcnt argument
 	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned -EINVAL for zero segments, so...
+	 * traditionally returned zero for zero segments, so...
 	 */
+	ret = 0;
 	if (nr_segs == 0)
 		goto out;
 
@@ -334,6 +335,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	 * First get the "struct iovec" from user memory and
 	 * verify all the pointers
 	 */
+	ret = -EINVAL;
 	if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0))
 		goto out;
 	if (!file->f_op)

include/asm-alpha/pal.h

@@ -45,7 +45,7 @@
 #define PAL_wrperfmon	57
 #define PAL_rdusp	58
 #define PAL_whami	60
-#define PAL_rtsys	61
+#define PAL_retsys	61
 #define PAL_rti		63
 
 #endif /* __ALPHA_PAL_H */

include/asm-alpha/unistd.h

@@ -331,19 +331,19 @@
 #define __NR_removexattr		391
 #define __NR_lremovexattr		392
 #define __NR_fremovexattr		393
-#define __NR_futex		394
-#define __NR_sched_setaffinity	395     
-#define __NR_sched_getaffinity	396
-#define __NR_tuxcall		397
-#define __NR_io_setup		398
-#define __NR_io_destroy		399
-#define __NR_io_getevents	400
-#define __NR_io_submit		401
-#define __NR_io_cancel		402
-#define __NR_alloc_hugepages	403
-#define __NR_free_hugepages	404
-#define __NR_exit_group		405
-
+#define __NR_futex			394
+#define __NR_sched_setaffinity		395     
+#define __NR_sched_getaffinity		396
+#define __NR_tuxcall			397
+#define __NR_io_setup			398
+#define __NR_io_destroy			399
+#define __NR_io_getevents		400
+#define __NR_io_submit			401
+#define __NR_io_cancel			402
+#define __NR_alloc_hugepages		403
+#define __NR_free_hugepages		404
+#define __NR_exit_group			405
+#define NR_SYSCALLS			406
 
 #if defined(__GNUC__)
 
@@ -598,7 +598,7 @@ static inline pid_t waitpid(int pid, int * wait_stat, int flags)
 	return sys_wait4(pid, wait_stat, flags, NULL);
 }
 
-#endif
+#endif /* __KERNEL_SYSCALLS__ */
 
 /*
  * "Conditional" syscalls

include/asm-generic/siginfo.h

@@ -91,7 +91,7 @@ typedef struct siginfo {
 #define __SI_FAULT	(3 << 16)
 #define __SI_CHLD	(4 << 16)
 #define __SI_RT		(5 << 16)
-#define __SI_CODE(T,N)	((T) << 16 | ((N) & 0xffff))
+#define __SI_CODE(T,N)	((T) | ((N) & 0xffff))
 #else
 #define __SI_KILL	0
 #define __SI_TIMER	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/pgtable.h

@@ -259,12 +259,21 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 		((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 #define pte_offset_kernel(dir, address) \
 	((pte_t *) pmd_page_kernel(*(dir)) +  __pte_offset(address))
+
+#if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + __pte_offset(address))
 #define pte_offset_map_nested(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE1) + __pte_offset(address))
 #define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0)
 #define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1)
+#else
+#define pte_offset_map(dir, address) \
+	((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address))
+#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+#endif
 
 #if defined(CONFIG_HIGHPTE) && defined(CONFIG_HIGHMEM4G)
 typedef u32 pte_addr_t;

include/asm-i386/timer.h

+#ifndef _ASMi386_TIMER_H
+#define _ASMi386_TIMER_H
+
+struct timer_opts{
+	/* probes and initializes timer. returns 1 on sucess, 0 on failure */
+	int (*init)(void);
+	/* called by the timer interrupt */
+	void (*mark_offset)(void);
+	/* called by gettimeofday. returns # ms since the last timer interrupt */
+	unsigned long (*get_offset)(void);
+};
+#define TICK_SIZE (tick_nsec / 1000)
+struct timer_opts* select_timer(void);
+#endif

include/linux/radix-tree.h

@@ -21,8 +21,6 @@
 
 struct radix_tree_node;
 
-#define RADIX_TREE_SLOT_RESERVED ((void *)~0UL)
-
 struct radix_tree_root {
 	unsigned int		height;
 	int			gfp_mask;
@@ -41,7 +39,6 @@ do {					\
 	(root)->rnode = NULL;		\
 } while (0)
 
-extern int radix_tree_reserve(struct radix_tree_root *, unsigned long, void ***);
 extern int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
 extern void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 extern int radix_tree_delete(struct radix_tree_root *, unsigned long);

kernel/timer.c

@@ -266,29 +266,31 @@ int del_timer(timer_t *timer)
 int del_timer_sync(timer_t *timer)
 {
 	tvec_base_t *base = tvec_bases;
-	int i, ret;
+	int i, ret = 0;
 
-	ret = del_timer(timer);
+del_again:
+	ret += del_timer(timer);
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for (i = 0; i < NR_CPUS; i++, base++) {
 		if (!cpu_online(i))
 			continue;
 		if (base->running_timer == timer) {
 			while (base->running_timer == timer) {
 				cpu_relax();
-				preempt_disable();
-				preempt_enable();
+				preempt_check_resched();
 			}
 			break;
 		}
-		base++;
 	}
+	if (timer_pending(timer))
+		goto del_again;
+
 	return ret;
 }
 #endif
 
 
-static void cascade(tvec_base_t *base, tvec_t *tv)
+static int cascade(tvec_base_t *base, tvec_t *tv)
 {
 	/* cascade all the timers from tv up one level */
 	struct list_head *head, *curr, *next;
@@ -310,7 +312,8 @@ static void cascade(tvec_base_t *base, tvec_t *tv)
 		curr = next;
 	}
 	INIT_LIST_HEAD(head);
-	tv->index = (tv->index + 1) & TVN_MASK;
+
+	return tv->index = (tv->index + 1) & TVN_MASK;
 }
 
 /***
@@ -322,26 +325,18 @@ static void cascade(tvec_base_t *base, tvec_t *tv)
  */
 static inline void __run_timers(tvec_base_t *base)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&base->lock, flags);
+	spin_lock_irq(&base->lock);
 	while ((long)(jiffies - base->timer_jiffies) >= 0) {
 		struct list_head *head, *curr;
 
 		/*
 		 * Cascade timers:
 		 */
-		if (!base->tv1.index) {
-			cascade(base, &base->tv2);
-			if (base->tv2.index == 1) {
-				cascade(base, &base->tv3);
-				if (base->tv3.index == 1) {
-					cascade(base, &base->tv4);
-					if (base->tv4.index == 1)
-						cascade(base, &base->tv5);
-				}
-			}
-		}
+		if (!base->tv1.index &&
+			(cascade(base, &base->tv2) == 1) &&
+				(cascade(base, &base->tv3) == 1) &&
+					cascade(base, &base->tv4) == 1)
+			cascade(base, &base->tv5);
 repeat:
 		head = base->tv1.vec + base->tv1.index;
 		curr = head->next;
@@ -360,7 +355,10 @@ static inline void __run_timers(tvec_base_t *base)
 			base->running_timer = timer;
 #endif
 			spin_unlock_irq(&base->lock);
-			fn(data);
+			if (!fn)
+				printk("Bad: timer %p has NULL fn. (data: %08lx)\n", timer, data);
+			else
+				fn(data);
 			spin_lock_irq(&base->lock);
 			goto repeat;
 		}
@@ -370,7 +368,7 @@ static inline void __run_timers(tvec_base_t *base)
 #if CONFIG_SMP
 	base->running_timer = NULL;
 #endif
-	spin_unlock_irqrestore(&base->lock, flags);
+	spin_unlock_irq(&base->lock);
 }
 
 /******************************************************************/

lib/radix-tree.c

@@ -77,7 +77,6 @@ static inline unsigned long radix_tree_maxindex(unsigned int height)
 	return index;
 }
 
-
 /*
  *	Extend a radix tree so it can store key @index.
  */
@@ -109,16 +108,15 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 	return 0;
 }
 
-
 /**
- *	radix_tree_reserve    -    reserve space in a radix tree
+ *	radix_tree_insert    -    insert into a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@pslot:		pointer to reserved slot
+ *	@item:		item to insert
  *
- *	Reserve a slot in a radix tree for the key @index.
+ *	Insert an item into the radix tree at position @index.
  */
-int radix_tree_reserve(struct radix_tree_root *root, unsigned long index, void ***pslot)
+int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL, *tmp, **slot;
 	unsigned int height, shift;
@@ -158,36 +156,11 @@ int radix_tree_reserve(struct radix_tree_root *root, unsigned long index, void *
 	if (node)
 		node->count++;
 
-	*pslot = (void **)slot;
-	**pslot = RADIX_TREE_SLOT_RESERVED;
+	*slot = item;
 	return 0;
 }
-
-EXPORT_SYMBOL(radix_tree_reserve);
-
-
-/**
- *	radix_tree_insert    -    insert into a radix tree
- *	@root:		radix tree root
- *	@index:		index key
- *	@item:		item to insert
- *
- *	Insert an item into the radix tree at position @index.
- */
-int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item)
-{
-	void **slot;
-	int error;
-
-	error = radix_tree_reserve(root, index, &slot);
-	if (!error)
-		*slot = item;
-	return error;
-}
-
 EXPORT_SYMBOL(radix_tree_insert);
 
-
 /**
  *	radix_tree_lookup    -    perform lookup operation on a radix tree
  *	@root:		radix tree root
@@ -267,8 +240,8 @@ __lookup(struct radix_tree_root *root, void **results, unsigned long index,
 out:
 	*next_index = index;
 	return nr_found;
-	
 }
+
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
@@ -371,7 +344,6 @@ int radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 
 	return 0;
 }
-
 EXPORT_SYMBOL(radix_tree_delete);
 
 static void radix_tree_node_ctor(void *node, kmem_cache_t *cachep, unsigned long flags)

mm/mremap.c

@@ -194,7 +194,8 @@ static inline unsigned long move_vma(struct vm_area_struct * vma,
 				prev->vm_end = next->vm_end;
 				__vma_unlink(mm, next, prev);
 				spin_unlock(&mm->page_table_lock);
-
+				if (vma == next)
+					vma = prev;
 				mm->map_count--;
 				kmem_cache_free(vm_area_cachep, next);
 			}

mm/swap_state.c

@@ -199,16 +199,14 @@ void delete_from_swap_cache(struct page *page)
 int move_to_swap_cache(struct page *page, swp_entry_t entry)
 {
 	struct address_space *mapping = page->mapping;
-	void **pslot;
 	int err;
 
 	write_lock(&swapper_space.page_lock);
 	write_lock(&mapping->page_lock);
 
-	err = radix_tree_reserve(&swapper_space.page_tree, entry.val, &pslot);
+	err = radix_tree_insert(&swapper_space.page_tree, entry.val, page);
 	if (!err) {
 		__remove_from_page_cache(page);
-		*pslot = page;
 		___add_to_page_cache(page, &swapper_space, entry.val);
 	}
 
@@ -231,7 +229,6 @@ int move_from_swap_cache(struct page *page, unsigned long index,
 		struct address_space *mapping)
 {
 	swp_entry_t entry;
-	void **pslot;
 	int err;
 
 	BUG_ON(!PageLocked(page));
@@ -243,10 +240,9 @@ int move_from_swap_cache(struct page *page, unsigned long index,
 	write_lock(&swapper_space.page_lock);
 	write_lock(&mapping->page_lock);
 
-	err = radix_tree_reserve(&mapping->page_tree, index, &pslot);
+	err = radix_tree_insert(&mapping->page_tree, index, page);
 	if (!err) {
 		__delete_from_swap_cache(page);
-		*pslot = page;
 		___add_to_page_cache(page, mapping, index);
 	}