21 files changed, 365 insertions, 119 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 289f448ac89..db259757dc8 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -265,7 +265,7 @@ config NUMA_EMU
 	  into virtual nodes when booted with "numa=fake=N", where N is the
 	  number of nodes. This is only useful for debugging.
 
-config DISCONTIGMEM
+config ARCH_DISCONTIGMEM_ENABLE
        bool
        depends on NUMA
        default y
@@ -274,6 +274,27 @@ config NUMA
        bool
        default n
 
+config ARCH_DISCONTIGMEM_ENABLE
+	def_bool y
+	depends on NUMA
+
+config ARCH_DISCONTIGMEM_DEFAULT
+	def_bool y
+	depends on NUMA
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y
+	depends on NUMA
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+	depends on !NUMA
+
+source "mm/Kconfig"
+
+config HAVE_ARCH_EARLY_PFN_TO_NID
+	def_bool y
+
 config HAVE_DEC_LOCK
 	bool
 	depends on SMP
@@ -381,6 +402,8 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
+source kernel/Kconfig.hz
+
 endmenu
 
 #
diff --git a/arch/x86_64/boot/install.sh b/arch/x86_64/boot/install.sh
index 90f2452b3b9..f17b40dfc0f 100644
--- a/arch/x86_64/boot/install.sh
+++ b/arch/x86_64/boot/install.sh
@@ -21,8 +21,8 @@
 
 # User may have a custom install script
 
-if [ -x ~/bin/installkernel ]; then exec ~/bin/installkernel "$@"; fi
-if [ -x /sbin/installkernel ]; then exec /sbin/installkernel "$@"; fi
+if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi
+if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi
 
 # Default install - same as make zlilo
 
diff --git a/arch/x86_64/ia32/ia32_signal.c b/arch/x86_64/ia32/ia32_signal.c
index fbd09b5126c..66e2821533d 100644
--- a/arch/x86_64/ia32/ia32_signal.c
+++ b/arch/x86_64/ia32/ia32_signal.c
@@ -428,8 +428,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
 	return (void __user *)((rsp - frame_size) & -8UL);
 }
 
-void ia32_setup_frame(int sig, struct k_sigaction *ka,
-			compat_sigset_t *set, struct pt_regs * regs)
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+		     compat_sigset_t *set, struct pt_regs * regs)
 {
 	struct sigframe __user *frame;
 	int err = 0;
@@ -514,14 +514,15 @@ void ia32_setup_frame(int sig, struct k_sigaction *ka,
 		current->comm, current->pid, frame, regs->rip, frame->pretcode);
 #endif
 
-	return;
+	return 1;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
+	return 0;
 }
 
-void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-			   compat_sigset_t *set, struct pt_regs * regs)
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+			compat_sigset_t *set, struct pt_regs * regs)
 {
 	struct rt_sigframe __user *frame;
 	int err = 0;
@@ -613,9 +614,9 @@ void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		current->comm, current->pid, frame, regs->rip, frame->pretcode);
 #endif
 
-	return;
+	return 1;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
+	return 0;
 }
-
diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index 504e6347499..c9a6b812e92 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -40,11 +40,7 @@ int fix_aperture __initdata = 1;
 
 static u32 __init allocate_aperture(void) 
 {
-#ifdef CONFIG_DISCONTIGMEM
 	pg_data_t *nd0 = NODE_DATA(0);
-#else
-	pg_data_t *nd0 = &contig_page_data;
-#endif	
 	u32 aper_size;
 	void *p; 
 
diff --git a/arch/x86_64/kernel/early_printk.c b/arch/x86_64/kernel/early_printk.c
index e3a19e8ebbf..9631c747c5e 100644
--- a/arch/x86_64/kernel/early_printk.c
+++ b/arch/x86_64/kernel/early_printk.c
@@ -2,20 +2,24 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include <linux/tty.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 
 /* Simple VGA output */
 
 #ifdef __i386__
+#include <asm/setup.h>
 #define VGABASE		(__ISA_IO_base + 0xb8000)
 #else
+#include <asm/bootsetup.h>
 #define VGABASE		((void __iomem *)0xffffffff800b8000UL)
 #endif
 
-#define MAX_YPOS	25
-#define MAX_XPOS	80
+#define MAX_YPOS	max_ypos
+#define MAX_XPOS	max_xpos
 
+static int max_ypos = 25, max_xpos = 80;
 static int current_ypos = 1, current_xpos = 0; 
 
 static void early_vga_write(struct console *con, const char *str, unsigned n)
@@ -196,7 +200,10 @@ int __init setup_early_printk(char *opt)
 	} else if (!strncmp(buf, "ttyS", 4)) { 
 		early_serial_init(buf);
 		early_console = &early_serial_console;		
-	} else if (!strncmp(buf, "vga", 3)) {
+	} else if (!strncmp(buf, "vga", 3)
+	           && SCREEN_INFO.orig_video_isVGA == 1) {
+		max_xpos = SCREEN_INFO.orig_video_cols;
+		max_ypos = SCREEN_INFO.orig_video_lines;
 		early_console = &early_vga_console; 
 	}
 	early_console_initialized = 1;
diff --git a/arch/x86_64/kernel/head64.c b/arch/x86_64/kernel/head64.c
index 0f8c78dcd38..cf6ab147a2a 100644
--- a/arch/x86_64/kernel/head64.c
+++ b/arch/x86_64/kernel/head64.c
@@ -94,7 +94,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	s = strstr(saved_command_line, "earlyprintk=");
 	if (s != NULL)
 		setup_early_printk(s);
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 	s = strstr(saved_command_line, "numa=");
 	if (s != NULL)
 		numa_setup(s+5);
diff --git a/arch/x86_64/kernel/i8259.c b/arch/x86_64/kernel/i8259.c
index 7873d9ba881..19eafa0aa95 100644
--- a/arch/x86_64/kernel/i8259.c
+++ b/arch/x86_64/kernel/i8259.c
@@ -157,14 +157,13 @@ static unsigned int startup_8259A_irq(unsigned int irq)
 }
 
 static struct hw_interrupt_type i8259A_irq_type = {
-	"XT-PIC",
-	startup_8259A_irq,
-	shutdown_8259A_irq,
-	enable_8259A_irq,
-	disable_8259A_irq,
-	mask_and_ack_8259A,
-	end_8259A_irq,
-	NULL
+	.typename = "XT-PIC",
+	.startup = startup_8259A_irq,
+	.shutdown = shutdown_8259A_irq,
+	.enable = enable_8259A_irq,
+	.disable = disable_8259A_irq,
+	.ack = mask_and_ack_8259A,
+	.end = end_8259A_irq,
 };
 
 /*
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index f77f8a0ff18..4e680f87a75 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -27,6 +27,8 @@
  *		<prasanna@in.ibm.com> adapted for x86_64
  * 2005-Mar	Roland McGrath <roland@redhat.com>
  *		Fixed to handle %rip-relative addressing mode correctly.
+ * 2005-May     Rusty Lynch <rusty.lynch@intel.com>
+ *              Added function return probes functionality
  */
 
 #include <linux/config.h>
@@ -37,18 +39,16 @@
 #include <linux/slab.h>
 #include <linux/preempt.h>
 #include <linux/moduleloader.h>
-
+#include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
 
 static DECLARE_MUTEX(kprobe_mutex);
 
-/* kprobe_status settings */
-#define KPROBE_HIT_ACTIVE	0x00000001
-#define KPROBE_HIT_SS		0x00000002
-
 static struct kprobe *current_kprobe;
 static unsigned long kprobe_status, kprobe_old_rflags, kprobe_saved_rflags;
+static struct kprobe *kprobe_prev;
+static unsigned long kprobe_status_prev, kprobe_old_rflags_prev, kprobe_saved_rflags_prev;
 static struct pt_regs jprobe_saved_regs;
 static long *jprobe_saved_rsp;
 static kprobe_opcode_t *get_insn_slot(void);
@@ -214,6 +214,21 @@ void arch_copy_kprobe(struct kprobe *p)
 		BUG_ON((s64) (s32) disp != disp); /* Sanity check.  */
 		*ripdisp = disp;
 	}
+	p->opcode = *p->addr;
+}
+
+void arch_arm_kprobe(struct kprobe *p)
+{
+	*p->addr = BREAKPOINT_INSTRUCTION;
+	flush_icache_range((unsigned long) p->addr,
+			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+}
+
+void arch_disarm_kprobe(struct kprobe *p)
+{
+	*p->addr = p->opcode;
+	flush_icache_range((unsigned long) p->addr,
+			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
 void arch_remove_kprobe(struct kprobe *p)
@@ -223,10 +238,29 @@ void arch_remove_kprobe(struct kprobe *p)
 	down(&kprobe_mutex);
 }
 
-static inline void disarm_kprobe(struct kprobe *p, struct pt_regs *regs)
+static inline void save_previous_kprobe(void)
 {
-	*p->addr = p->opcode;
-	regs->rip = (unsigned long)p->addr;
+	kprobe_prev = current_kprobe;
+	kprobe_status_prev = kprobe_status;
+	kprobe_old_rflags_prev = kprobe_old_rflags;
+	kprobe_saved_rflags_prev = kprobe_saved_rflags;
+}
+
+static inline void restore_previous_kprobe(void)
+{
+	current_kprobe = kprobe_prev;
+	kprobe_status = kprobe_status_prev;
+	kprobe_old_rflags = kprobe_old_rflags_prev;
+	kprobe_saved_rflags = kprobe_saved_rflags_prev;
+}
+
+static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs)
+{
+	current_kprobe = p;
+	kprobe_saved_rflags = kprobe_old_rflags
+		= (regs->eflags & (TF_MASK | IF_MASK));
+	if (is_IF_modifier(p->ainsn.insn))
+		kprobe_saved_rflags &= ~IF_MASK;
 }
 
 static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
@@ -240,6 +274,50 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->rip = (unsigned long)p->ainsn.insn;
 }
 
+struct task_struct  *arch_get_kprobe_task(void *ptr)
+{
+	return ((struct thread_info *) (((unsigned long) ptr) &
+					(~(THREAD_SIZE -1))))->task;
+}
+
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+	unsigned long *sara = (unsigned long *)regs->rsp;
+	struct kretprobe_instance *ri;
+	static void *orig_ret_addr;
+
+	/*
+	 * Save the return address when the return probe hits
+	 * the first time, and use it to populate the (krprobe
+	 * instance)->ret_addr for subsequent return probes at
+	 * the same addrress since stack address would have
+	 * the kretprobe_trampoline by then.
+	 */
+	if (((void*) *sara) != kretprobe_trampoline)
+		orig_ret_addr = (void*) *sara;
+
+	if ((ri = get_free_rp_inst(rp)) != NULL) {
+		ri->rp = rp;
+		ri->stack_addr = sara;
+		ri->ret_addr = orig_ret_addr;
+		add_rp_inst(ri);
+		/* Replace the return addr with trampoline addr */
+		*sara = (unsigned long) &kretprobe_trampoline;
+	} else {
+		rp->nmissed++;
+	}
+}
+
+void arch_kprobe_flush_task(struct task_struct *tk)
+{
+	struct kretprobe_instance *ri;
+	while ((ri = get_rp_inst_tsk(tk)) != NULL) {
+		*((unsigned long *)(ri->stack_addr)) =
+					(unsigned long) ri->ret_addr;
+		recycle_rp_inst(ri);
+	}
+}
+
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled thorough out this function.
@@ -264,9 +342,30 @@ int kprobe_handler(struct pt_regs *regs)
 				regs->eflags |= kprobe_saved_rflags;
 				unlock_kprobes();
 				goto no_kprobe;
+			} else if (kprobe_status == KPROBE_HIT_SSDONE) {
+				/* TODO: Provide re-entrancy from
+				 * post_kprobes_handler() and avoid exception
+				 * stack corruption while single-stepping on
+				 * the instruction of the new probe.
+				 */
+				arch_disarm_kprobe(p);
+				regs->rip = (unsigned long)p->addr;
+				ret = 1;
+			} else {
+				/* We have reentered the kprobe_handler(), since
+				 * another probe was hit while within the
+				 * handler. We here save the original kprobe
+				 * variables and just single step on instruction
+				 * of the new probe without calling any user
+				 * handlers.
+				 */
+				save_previous_kprobe();
+				set_current_kprobe(p, regs);
+				p->nmissed++;
+				prepare_singlestep(p, regs);
+				kprobe_status = KPROBE_REENTER;
+				return 1;
 			}
-			disarm_kprobe(p, regs);
-			ret = 1;
 		} else {
 			p = current_kprobe;
 			if (p->break_handler && p->break_handler(p, regs)) {
@@ -296,11 +395,7 @@ int kprobe_handler(struct pt_regs *regs)
 	}
 
 	kprobe_status = KPROBE_HIT_ACTIVE;
-	current_kprobe = p;
-	kprobe_saved_rflags = kprobe_old_rflags
-	    = (regs->eflags & (TF_MASK | IF_MASK));
-	if (is_IF_modifier(p->ainsn.insn))
-		kprobe_saved_rflags &= ~IF_MASK;
+	set_current_kprobe(p, regs);
 
 	if (p->pre_handler && p->pre_handler(p, regs))
 		/* handler has already set things up, so skip ss setup */
@@ -317,6 +412,55 @@ no_kprobe:
 }
 
 /*
+ * For function-return probes, init_kprobes() establishes a probepoint
+ * here. When a retprobed function returns, this probe is hit and
+ * trampoline_probe_handler() runs, calling the kretprobe's handler.
+ */
+ void kretprobe_trampoline_holder(void)
+ {
+ 	asm volatile (  ".global kretprobe_trampoline\n"
+ 			"kretprobe_trampoline: \n"
+ 			"nop\n");
+ }
+
+/*
+ * Called when we hit the probe point at kretprobe_trampoline
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct task_struct *tsk;
+	struct kretprobe_instance *ri;
+	struct hlist_head *head;
+	struct hlist_node *node;
+	unsigned long *sara = (unsigned long *)regs->rsp - 1;
+
+	tsk = arch_get_kprobe_task(sara);
+	head = kretprobe_inst_table_head(tsk);
+
+	hlist_for_each_entry(ri, node, head, hlist) {
+		if (ri->stack_addr == sara && ri->rp) {
+			if (ri->rp->handler)
+				ri->rp->handler(ri, regs);
+		}
+	}
+	return 0;
+}
+
+void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
+						unsigned long flags)
+{
+	struct kretprobe_instance *ri;
+	/* RA already popped */
+	unsigned long *sara = ((unsigned long *)regs->rsp) - 1;
+
+	while ((ri = get_rp_inst(sara))) {
+		regs->rip = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri);
+	}
+	regs->eflags &= ~TF_MASK;
+}
+
+/*
  * Called after single-stepping.  p->addr is the address of the
  * instruction whose first byte has been replaced by the "int 3"
  * instruction.  To avoid the SMP problems that can occur when we
@@ -401,13 +545,23 @@ int post_kprobe_handler(struct pt_regs *regs)
 	if (!kprobe_running())
 		return 0;
 
-	if (current_kprobe->post_handler)
+	if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
+		kprobe_status = KPROBE_HIT_SSDONE;
 		current_kprobe->post_handler(current_kprobe, regs, 0);
+	}
 
-	resume_execution(current_kprobe, regs);
+	if (current_kprobe->post_handler != trampoline_post_handler)
+		resume_execution(current_kprobe, regs);
 	regs->eflags |= kprobe_saved_rflags;
 
-	unlock_kprobes();
+	/* Restore the original saved kprobes variables and continue. */
+	if (kprobe_status == KPROBE_REENTER) {
+		restore_previous_kprobe();
+		goto out;
+	} else {
+		unlock_kprobes();
+	}
+out:
 	preempt_enable_no_resched();
 
 	/*
diff --git a/arch/x86_64/kernel/mpparse.c b/arch/x86_64/kernel/mpparse.c
index 61a63be6b29..9c5aa2a790c 100644
--- a/arch/x86_64/kernel/mpparse.c
+++ b/arch/x86_64/kernel/mpparse.c
@@ -23,6 +23,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/acpi.h>
+#include <linux/module.h>
 
 #include <asm/smp.h>
 #include <asm/mtrr.h>
@@ -45,7 +46,8 @@ int acpi_found_madt;
 int apic_version [MAX_APICS];
 unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 };
 int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 };
-cpumask_t pci_bus_to_cpumask [256] = { [0 ... 255] = CPU_MASK_ALL };
+unsigned char pci_bus_to_node [256];
+EXPORT_SYMBOL(pci_bus_to_node);
 
 static int mp_current_pci_id = 0;
 /* I/O APIC entries */
@@ -904,11 +906,20 @@ void __init mp_config_acpi_legacy_irqs (void)
 	return;
 }
 
+#define MAX_GSI_NUM	4096
+
 int mp_register_gsi(u32 gsi, int edge_level, int active_high_low)
 {
 	int			ioapic = -1;
 	int			ioapic_pin = 0;
 	int			idx, bit = 0;
+	static int		pci_irq = 16;
+	/*
+	 * Mapping between Global System Interrupts, which
+	 * represent all possible interrupts, to the IRQs
+	 * assigned to actual devices.
+	 */
+	static int		gsi_to_irq[MAX_GSI_NUM];
 
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
@@ -943,11 +954,21 @@ int mp_register_gsi(u32 gsi, int edge_level, int active_high_low)
 	if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
 		Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
 			mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-		return gsi;
+		return gsi_to_irq[gsi];
 	}
 
 	mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit);
 
+	if (edge_level) {
+		/*
+		 * For PCI devices assign IRQs in order, avoiding gaps
+		 * due to unused I/O APIC pins.
+		 */
+		int irq = gsi;
+		gsi = pci_irq++;
+		gsi_to_irq[irq] = gsi;
+	}
+
 	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
 		edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1,
 		active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1);
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index dce8bab4306..e59d1f9d616 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -34,6 +34,7 @@
 #include <linux/ptrace.h>
 #include <linux/utsname.h>
 #include <linux/random.h>
+#include <linux/kprobes.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -293,6 +294,14 @@ void exit_thread(void)
 {
 	struct task_struct *me = current;
 	struct thread_struct *t = &me->thread;
+
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(me);
+
 	if (me->thread.io_bitmap_ptr) { 
 		struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
 
@@ -312,6 +321,13 @@ void flush_thread(void)
 	struct task_struct *tsk = current;
 	struct thread_info *t = current_thread_info();
 
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(tsk);
+
 	if (t->flags & _TIF_ABI_PENDING)
 		t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);
 
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 99f038ede23..000015dd5a8 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -40,6 +40,8 @@
 #include <linux/acpi.h>
 #include <linux/kallsyms.h>
 #include <linux/edd.h>
+#include <linux/mmzone.h>
+
 #include <asm/mtrr.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -348,7 +350,7 @@ static __init void parse_cmdline_early (char ** cmdline_p)
 		if (!memcmp(from, "mem=", 4))
 			parse_memopt(from+4, &from); 
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 		if (!memcmp(from, "numa=", 5))
 			numa_setup(from+5); 
 #endif
@@ -377,17 +379,20 @@ static __init void parse_cmdline_early (char ** cmdline_p)
 	*cmdline_p = command_line;
 }
 
-#ifndef CONFIG_DISCONTIGMEM
-static void __init contig_initmem_init(void)
+#ifndef CONFIG_NUMA
+static void __init
+contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 {
-        unsigned long bootmap_size, bootmap; 
-        bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-        bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size);
-        if (bootmap == -1L) 
-                panic("Cannot find bootmem map of size %ld\n",bootmap_size);
-        bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
-        e820_bootmem_free(&contig_page_data, 0, end_pfn << PAGE_SHIFT); 
-        reserve_bootmem(bootmap, bootmap_size);
+	unsigned long bootmap_size, bootmap;
+
+	memory_present(0, start_pfn, end_pfn);
+	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
+	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size);
+	if (bootmap == -1L)
+		panic("Cannot find bootmem map of size %ld\n",bootmap_size);
+	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
+	e820_bootmem_free(NODE_DATA(0), 0, end_pfn << PAGE_SHIFT);
+	reserve_bootmem(bootmap, bootmap_size);
 } 
 #endif
 
@@ -554,10 +559,10 @@ void __init setup_arch(char **cmdline_p)
 	acpi_numa_init();
 #endif
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 	numa_initmem_init(0, end_pfn); 
 #else
-	contig_initmem_init(); 
+	contig_initmem_init(0, end_pfn);
 #endif
 
 	/* Reserve direct mapping */
@@ -618,6 +623,8 @@ void __init setup_arch(char **cmdline_p)
 		}
 	}
 #endif
+
+	sparse_init();
 	paging_init();
 
 	check_ioapic();
diff --git a/arch/x86_64/kernel/signal.c b/arch/x86_64/kernel/signal.c
index 429c0269dc4..98b7ba95d58 100644
--- a/arch/x86_64/kernel/signal.c
+++ b/arch/x86_64/kernel/signal.c
@@ -34,9 +34,9 @@
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                sigset_t *set, struct pt_regs * regs); 
-void ia32_setup_frame(int sig, struct k_sigaction *ka,
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
             sigset_t *set, struct pt_regs * regs); 
 
 asmlinkage long
@@ -238,7 +238,7 @@ get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
 	return (void __user *)round_down(rsp - size, 16); 
 }
 
-static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			   sigset_t *set, struct pt_regs * regs)
 {
 	struct rt_sigframe __user *frame;
@@ -327,20 +327,23 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		current->comm, current->pid, frame, regs->rip, frame->pretcode);
 #endif
 
-	return;
+	return 1;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
+	return 0;
 }
 
 /*
  * OK, we're invoking a handler
  */	
 
-static void
+static int
 handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 		sigset_t *oldset, struct pt_regs *regs)
 {
+	int ret;
+
 #ifdef DEBUG_SIG
 	printk("handle_signal pid:%d sig:%lu rip:%lx rsp:%lx regs=%p\n",
 		current->pid, sig,
@@ -384,20 +387,22 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 #ifdef CONFIG_IA32_EMULATION
 	if (test_thread_flag(TIF_IA32)) {
 		if (ka->sa.sa_flags & SA_SIGINFO)
-			ia32_setup_rt_frame(sig, ka, info, oldset, regs);
+			ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
 		else
-			ia32_setup_frame(sig, ka, oldset, regs);
+			ret = ia32_setup_frame(sig, ka, oldset, regs);
 	} else 
 #endif
-	setup_rt_frame(sig, ka, info, oldset, regs);
+	ret = setup_rt_frame(sig, ka, info, oldset, regs);
 
-	if (!(ka->sa.sa_flags & SA_NODEFER)) {
+	if (ret && !(ka->sa.sa_flags & SA_NODEFER)) {
 		spin_lock_irq(&current->sighand->siglock);
 		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
 		sigaddset(&current->blocked,sig);
 		recalc_sigpending();
 		spin_unlock_irq(&current->sighand->siglock);
 	}
+
+	return ret;
 }
 
 /*
@@ -417,7 +422,7 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 	 * kernel mode. Just return without doing anything
 	 * if so.
 	 */
-	if ((regs->cs & 3) != 3)
+	if (!user_mode(regs))
 		return 1;
 
 	if (try_to_freeze(0))
@@ -434,11 +439,10 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 		 * inside the kernel.
 		 */
 		if (current->thread.debugreg7)
-			asm volatile("movq %0,%%db7"	: : "r" (current->thread.debugreg7));
+			set_debugreg(current->thread.debugreg7, 7);
 
 		/* Whee!  Actually deliver the signal.  */
-		handle_signal(signr, &info, &ka, oldset, regs);
-		return 1;
+		return handle_signal(signr, &info, &ka, oldset, regs);
 	}
 
  no_signal:
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index fb8c809b4cd..66bf6ddeb0c 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -64,6 +64,7 @@ static int notsc __initdata = 0;
 unsigned int cpu_khz;					/* TSC clocks / usec, not used here */
 static unsigned long hpet_period;			/* fsecs / HPET clock */
 unsigned long hpet_tick;				/* HPET clocks / interrupt */
+static int hpet_use_timer;
 unsigned long vxtime_hz = PIT_TICK_RATE;
 int report_lost_ticks;				/* command line option */
 unsigned long long monotonic_base;
@@ -105,7 +106,9 @@ static inline unsigned int do_gettimeoffset_tsc(void)
 
 static inline unsigned int do_gettimeoffset_hpet(void)
 {
-	return ((hpet_readl(HPET_COUNTER) - vxtime.last) * vxtime.quot) >> 32;
+	/* cap counter read to one tick to avoid inconsistencies */
+	unsigned long counter = hpet_readl(HPET_COUNTER) - vxtime.last;
+	return (min(counter,hpet_tick) * vxtime.quot) >> 32;
 }
 
 unsigned int (*do_gettimeoffset)(void) = do_gettimeoffset_tsc;
@@ -301,7 +304,7 @@ unsigned long long monotonic_clock(void)
 
 			last_offset = vxtime.last;
 			base = monotonic_base;
-			this_offset = hpet_readl(HPET_T0_CMP) - hpet_tick;
+			this_offset = hpet_readl(HPET_COUNTER);
 
 		} while (read_seqretry(&xtime_lock, seq));
 		offset = (this_offset - last_offset);
@@ -377,7 +380,14 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 
 	write_seqlock(&xtime_lock);
 
-	if (vxtime.hpet_address) {
+	if (vxtime.hpet_address)
+		offset = hpet_readl(HPET_COUNTER);
+
+	if (hpet_use_timer) {
+		/* if we're using the hpet timer functionality,
+		 * we can more accurately know the counter value
+		 * when the timer interrupt occured.
+		 */
 		offset = hpet_readl(HPET_T0_CMP) - hpet_tick;
 		delay = hpet_readl(HPET_COUNTER) - offset;
 	} else {
@@ -803,17 +813,18 @@ static int hpet_timer_stop_set_go(unsigned long tick)
  * Set up timer 0, as periodic with first interrupt to happen at hpet_tick,
  * and period also hpet_tick.
  */
-
-	hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
+	if (hpet_use_timer) {
+		hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
 		    HPET_TN_32BIT, HPET_T0_CFG);
-	hpet_writel(hpet_tick, HPET_T0_CMP);
-	hpet_writel(hpet_tick, HPET_T0_CMP); /* AK: why twice? */
-
+		hpet_writel(hpet_tick, HPET_T0_CMP);
+		hpet_writel(hpet_tick, HPET_T0_CMP); /* AK: why twice? */
+		cfg |= HPET_CFG_LEGACY;
+	}
 /*
  * Go!
  */
 
-	cfg |= HPET_CFG_ENABLE | HPET_CFG_LEGACY;
+	cfg |= HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 
 	return 0;
@@ -834,8 +845,7 @@ static int hpet_init(void)
 
 	id = hpet_readl(HPET_ID);
 
-	if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER) ||
-	    !(id & HPET_ID_LEGSUP))
+	if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER))
 		return -1;
 
 	hpet_period = hpet_readl(HPET_PERIOD);
@@ -845,6 +855,8 @@ static int hpet_init(void)
 	hpet_tick = (1000000000L * (USEC_PER_SEC / HZ) + hpet_period / 2) /
 		hpet_period;
 
+	hpet_use_timer = (id & HPET_ID_LEGSUP);
+
 	return hpet_timer_stop_set_go(hpet_tick);
 }
 
@@ -901,9 +913,11 @@ void __init time_init(void)
 	set_normalized_timespec(&wall_to_monotonic,
 	                        -xtime.tv_sec, -xtime.tv_nsec);
 
-	if (!hpet_init()) {
+	if (!hpet_init())
                 vxtime_hz = (1000000000000000L + hpet_period / 2) /
 			hpet_period;
+
+	if (hpet_use_timer) {
 		cpu_khz = hpet_calibrate_tsc();
 		timename = "HPET";
 #ifdef CONFIG_X86_PM_TIMER
@@ -968,7 +982,7 @@ void __init time_init_gtod(void)
 	if (unsynchronized_tsc())
 		notsc = 1;
 	if (vxtime.hpet_address && notsc) {
-		timetype = "HPET";
+		timetype = hpet_use_timer ? "HPET" : "PIT/HPET";
 		vxtime.last = hpet_readl(HPET_T0_CMP) - hpet_tick;
 		vxtime.mode = VXTIME_HPET;
 		do_gettimeoffset = do_gettimeoffset_hpet;
@@ -983,7 +997,7 @@ void __init time_init_gtod(void)
 		printk(KERN_INFO "Disabling vsyscall due to use of PM timer\n");
 #endif
 	} else {
-		timetype = vxtime.hpet_address ? "HPET/TSC" : "PIT/TSC";
+		timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
 		vxtime.mode = VXTIME_TSC;
 	}
 
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 3dfec8fdabc..121646fc43f 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -274,7 +274,7 @@ EXPORT_SYMBOL(dump_stack);
 void show_registers(struct pt_regs *regs)
 {
 	int i;
-	int in_kernel = (regs->cs & 3) == 0;
+	int in_kernel = !user_mode(regs);
 	unsigned long rsp;
 	const int cpu = safe_smp_processor_id(); 
 	struct task_struct *cur = cpu_pda[cpu].pcurrent; 
@@ -318,7 +318,7 @@ void handle_BUG(struct pt_regs *regs)
 	struct bug_frame f;
 	char tmp;
 
-	if (regs->cs & 3)
+	if (user_mode(regs))
 		return; 
 	if (__copy_from_user(&f, (struct bug_frame *) regs->rip, 
 			     sizeof(struct bug_frame)))
@@ -437,7 +437,7 @@ static void do_trap(int trapnr, int signr, char *str,
        }
 #endif
 
-	if ((regs->cs & 3)  != 0) { 
+	if (user_mode(regs)) {
 		struct task_struct *tsk = current;
 
 		if (exception_trace && unhandled_signal(tsk, signr))
@@ -522,7 +522,7 @@ asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
        }
 #endif
 
-	if ((regs->cs & 3)!=0) { 
+	if (user_mode(regs)) {
 		struct task_struct *tsk = current;
 
 		if (exception_trace && unhandled_signal(tsk, SIGSEGV))
@@ -638,7 +638,7 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs)
 	if (eregs == (struct pt_regs *)eregs->rsp)
 		;
 	/* Exception from user space */
-	else if (eregs->cs & 3)
+	else if (user_mode(eregs))
 		regs = ((struct pt_regs *)current->thread.rsp0) - 1;
 	/* Exception from kernel and interrupts are enabled. Move to
  	   kernel process stack. */
@@ -669,7 +669,7 @@ asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code)
        }
 #endif
 
-	asm("movq %%db6,%0" : "=r" (condition));
+	get_debugreg(condition, 6);
 
 	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
 						SIGTRAP) == NOTIFY_STOP)
@@ -697,7 +697,7 @@ asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code)
 		 * allowing programs to debug themselves without the ptrace()
 		 * interface.
 		 */
-                if ((regs->cs & 3) == 0)
+                if (!user_mode(regs))
                        goto clear_TF_reenable;
 		/*
 		 * Was the TF flag set by a debugger? If so, clear it now,
@@ -715,13 +715,13 @@ asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code)
 	info.si_signo = SIGTRAP;
 	info.si_errno = 0;
 	info.si_code = TRAP_BRKPT;
-	if ((regs->cs & 3) == 0) 
+	if (!user_mode(regs))
 		goto clear_dr7; 
 
 	info.si_addr = (void __user *)regs->rip;
 	force_sig_info(SIGTRAP, &info, tsk);	
 clear_dr7:
-	asm volatile("movq %0,%%db7"::"r"(0UL));
+	set_debugreg(0UL, 7);
 	return;
 
 clear_TF_reenable:
@@ -756,7 +756,7 @@ asmlinkage void do_coprocessor_error(struct pt_regs *regs)
 	unsigned short cwd, swd;
 
 	conditional_sti(regs);
-	if ((regs->cs & 3) == 0 &&
+	if (!user_mode(regs) &&
 	    kernel_math_error(regs, "kernel x87 math error"))
 		return;
 
@@ -822,7 +822,7 @@ asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
 	unsigned short mxcsr;
 
 	conditional_sti(regs);
-	if ((regs->cs & 3) == 0 &&
+	if (!user_mode(regs) &&
         	kernel_math_error(regs, "kernel simd math error"))
 		return;
 
diff --git a/arch/x86_64/lib/delay.c b/arch/x86_64/lib/delay.c
index aed61a668a1..33a873a3c22 100644
--- a/arch/x86_64/lib/delay.c
+++ b/arch/x86_64/lib/delay.c
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <asm/delay.h>
+#include <asm/msr.h>
 
 #ifdef CONFIG_SMP
 #include <asm/smp.h>
@@ -19,6 +20,12 @@
 
 int x86_udelay_tsc = 0;		/* Delay via TSC */
 
+int read_current_timer(unsigned long *timer_value)
+{
+	rdtscll(*timer_value);
+	return 0;
+}
+
 void __delay(unsigned long loops)
 {
 	unsigned bclock, now;
diff --git a/arch/x86_64/mm/Makefile b/arch/x86_64/mm/Makefile
index 66c354ad80c..1d232a87f11 100644
--- a/arch/x86_64/mm/Makefile
+++ b/arch/x86_64/mm/Makefile
@@ -4,7 +4,7 @@
 
 obj-y	 := init.o fault.o ioremap.o extable.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_DISCONTIGMEM) += numa.o
+obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_K8_NUMA) += k8topology.o
 obj-$(CONFIG_ACPI_NUMA) += srat.o
 
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 57d3ab15a5c..2f187986f94 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -74,7 +74,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr,
 	instr = (unsigned char *)convert_rip_to_linear(current, regs);
 	max_instr = instr + 15;
 
-	if ((regs->cs & 3) != 0 && instr >= (unsigned char *)TASK_SIZE)
+	if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
 		return 0;
 
 	while (scan_more && instr < max_instr) { 
@@ -106,7 +106,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr,
 			/* Could check the LDT for lm, but for now it's good
 			   enough to assume that long mode only uses well known
 			   segments or kernel. */
-			scan_more = ((regs->cs & 3) == 0) || (regs->cs == __USER_CS);
+			scan_more = (!user_mode(regs)) || (regs->cs == __USER_CS);
 			break;
 			
 		case 0x60:
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index dbe53b4c7e6..72e4b364ed7 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -318,7 +318,7 @@ void zap_low_mappings(void)
 	flush_tlb_all();
 }
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
 	{
@@ -427,13 +427,16 @@ void __init mem_init(void)
 	reservedpages = 0;
 
 	/* this will put all low memory onto the freelists */
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 	totalram_pages += numa_free_all_bootmem();
 	tmp = 0;
 	/* should count reserved pages here for all nodes */ 
 #else
+
+#ifdef CONFIG_FLATMEM
 	max_mapnr = end_pfn;
 	if (!mem_map) BUG();
+#endif
 
 	totalram_pages += free_all_bootmem();
 
@@ -515,7 +518,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len) 
 { 
 	/* Should check here against the e820 map to avoid double free */ 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 	int nid = phys_to_nid(phys);
   	reserve_bootmem_node(NODE_DATA(nid), phys, len);
 #else       		
diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c
index 58aac23760e..6972df480d2 100644
--- a/arch/x86_64/mm/ioremap.c
+++ b/arch/x86_64/mm/ioremap.c
@@ -178,7 +178,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS)
 		return (__force void __iomem *)phys_to_virt(phys_addr);
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index fd9f25d7a6c..84cde796ecb 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -66,6 +66,13 @@ int __init compute_hash_shift(struct node *nodes, int numnodes)
 	return -1; 
 }
 
+#ifdef CONFIG_SPARSEMEM
+int early_pfn_to_nid(unsigned long pfn)
+{
+	return phys_to_nid(pfn << PAGE_SHIFT);
+}
+#endif
+
 /* Initialize bootmem allocator for a node */
 void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 { 
@@ -80,6 +87,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 	start_pfn = start >> PAGE_SHIFT;
 	end_pfn = end >> PAGE_SHIFT;
 
+	memory_present(nodeid, start_pfn, end_pfn);
 	nodedata_phys = find_e820_area(start, end, pgdat_size); 
 	if (nodedata_phys == -1L) 
 		panic("Cannot find memory pgdat in node %d\n", nodeid);
diff --git a/arch/x86_64/pci/k8-bus.c b/arch/x86_64/pci/k8-bus.c
index 62349c78db5..7e7d0c2a002 100644
--- a/arch/x86_64/pci/k8-bus.c
+++ b/arch/x86_64/pci/k8-bus.c
@@ -53,25 +53,11 @@ fill_mp_bus_to_cpumask(void)
 				for (j = SECONDARY_LDT_BUS_NUMBER(ldtbus);
 				     j <= SUBORDINATE_LDT_BUS_NUMBER(ldtbus);
 				     j++)
-					pci_bus_to_cpumask[j] =
-						node_to_cpumask(NODE_ID(nid));
+					pci_bus_to_node[j] = NODE_ID(nid);
 			}
 		}
 	}
 
-	/* quick sanity check */
-	printed = 0;
-	for (i = 0; i < 256; i++) {
-		if (cpus_empty(pci_bus_to_cpumask[i])) {
-			pci_bus_to_cpumask[i] = CPU_MASK_ALL;
-			if (printed)
-				continue;
-			printk(KERN_ERR
-			       "k8-bus.c: some busses have empty cpu mask\n");
-			printed = 1;
-		}
-	}
-
 	return 0;
 }