Merge branch 'master' into upstream

19 files changed, 298 insertions, 76 deletions

diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index b2751eadbc5..6189b0c28d6 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -494,7 +494,7 @@ config HIGHMEM64G
 endchoice
 
 choice
-	depends on EXPERIMENTAL && !X86_PAE
+	depends on EXPERIMENTAL
 	prompt "Memory split" if EMBEDDED
 	default VMSPLIT_3G
 	help
@@ -516,6 +516,7 @@ choice
 	config VMSPLIT_3G
 		bool "3G/1G user/kernel split"
 	config VMSPLIT_3G_OPT
+		depends on !HIGHMEM
 		bool "3G/1G user/kernel split (for full 1G low memory)"
 	config VMSPLIT_2G
 		bool "2G/2G user/kernel split"
@@ -794,6 +795,7 @@ config HOTPLUG_CPU
 config COMPAT_VDSO
 	bool "Compat VDSO support"
 	default y
+	depends on !PARAVIRT
 	help
 	  Map the VDSO to the predictable old-style address too.
 	---help---
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 8591f2fa920..ff9ce4b5eaa 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -1154,9 +1154,11 @@ out:
 
 static void set_time(void)
 {
+	struct timespec ts;
 	if (got_clock_diff) {	/* Must know time zone in order to set clock */
-		xtime.tv_sec = get_cmos_time() + clock_cmos_diff;
-		xtime.tv_nsec = 0; 
+		ts.tv_sec = get_cmos_time() + clock_cmos_diff;
+		ts.tv_nsec = 0;
+		do_settimeofday(&ts);
 	} 
 }
 
@@ -1232,13 +1234,8 @@ static int suspend(int vetoable)
 	restore_processor_state();
 
 	local_irq_disable();
-	write_seqlock(&xtime_lock);
-	spin_lock(&i8253_lock);
-	reinit_timer();
 	set_time();
-
-	spin_unlock(&i8253_lock);
-	write_sequnlock(&xtime_lock);
+	reinit_timer();
 
 	if (err == APM_NO_ERROR)
 		err = APM_SUCCESS;
@@ -1365,9 +1362,7 @@ static void check_events(void)
 			ignore_bounce = 1;
 			if ((event != APM_NORMAL_RESUME)
 			    || (ignore_normal_resume == 0)) {
-				write_seqlock_irq(&xtime_lock);
 				set_time();
-				write_sequnlock_irq(&xtime_lock);
 				device_resume();
 				pm_send_all(PM_RESUME, (void *)0);
 				queue_event(event, NULL);
@@ -1383,9 +1378,7 @@ static void check_events(void)
 			break;
 
 		case APM_UPDATE_TIME:
-			write_seqlock_irq(&xtime_lock);
 			set_time();
-			write_sequnlock_irq(&xtime_lock);
 			break;
 
 		case APM_CRITICAL_SUSPEND:
@@ -2339,6 +2332,7 @@ static int __init apm_init(void)
 	ret = kernel_thread(apm, NULL, CLONE_KERNEL | SIGCHLD);
 	if (ret < 0) {
 		printk(KERN_ERR "apm: disabled - Unable to start kernel thread.\n");
+		remove_proc_entry("apm", NULL);
 		return -ENOMEM;
 	}
 
@@ -2348,7 +2342,13 @@ static int __init apm_init(void)
 		return 0;
 	}
 
-	misc_register(&apm_device);
+	/*
+	 * Note we don't actually care if the misc_device cannot be registered.
+	 * this driver can do its job without it, even if userspace can't
+	 * control it.  just log the error
+	 */
+	if (misc_register(&apm_device))
+		printk(KERN_WARNING "apm: Could not register misc device.\n");
 
 	if (HZ != 100)
 		idle_period = (idle_period * HZ) / 100;
diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c
index 169ac8e0db6..0b61eed8bbd 100644
--- a/arch/i386/kernel/cpu/mtrr/generic.c
+++ b/arch/i386/kernel/cpu/mtrr/generic.c
@@ -243,7 +243,7 @@ static DEFINE_SPINLOCK(set_atomicity_lock);
  * has been called.
  */
 
-static void prepare_set(void)
+static void prepare_set(void) __acquires(set_atomicity_lock)
 {
 	unsigned long cr0;
 
@@ -274,7 +274,7 @@ static void prepare_set(void)
 	mtrr_wrmsr(MTRRdefType_MSR, deftype_lo & 0xf300UL, deftype_hi);
 }
 
-static void post_set(void)
+static void post_set(void) __releases(set_atomicity_lock)
 {
 	/*  Flush TLBs (no need to flush caches - they are disabled)  */
 	__flush_tlb();
diff --git a/arch/i386/kernel/efi_stub.S b/arch/i386/kernel/efi_stub.S
index d3ee73a3eee..ef00bb77d7e 100644
--- a/arch/i386/kernel/efi_stub.S
+++ b/arch/i386/kernel/efi_stub.S
@@ -7,7 +7,6 @@
 
 #include <linux/linkage.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
 
 /*
  * efi_call_phys(void *, ...) is a function with variable parameters.
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 54cfeabbc5e..84278e0093a 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -145,14 +145,10 @@ real_mode_gdt_entries [3] =
 	0x000092000100ffffULL	/* 16-bit real-mode 64k data at 0x00000100 */
 };
 
-static struct
-{
-	unsigned short       size __attribute__ ((packed));
-	unsigned long long * base __attribute__ ((packed));
-}
-real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, real_mode_gdt_entries },
-real_mode_idt = { 0x3ff, NULL },
-no_idt = { 0, NULL };
+static struct Xgt_desc_struct
+real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries },
+real_mode_idt = { 0x3ff, 0 },
+no_idt = { 0, 0 };
 
 
 /* This is 16-bit protected mode code to disable paging and the cache,
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index f1682206d30..16d99444cf6 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -53,6 +53,7 @@
 #include <asm/apic.h>
 #include <asm/e820.h>
 #include <asm/mpspec.h>
+#include <asm/mmzone.h>
 #include <asm/setup.h>
 #include <asm/arch_hooks.h>
 #include <asm/sections.h>
@@ -934,6 +935,24 @@ static void __init parse_cmdline_early (char ** cmdline_p)
 }
 
 /*
+ * reservetop=size reserves a hole at the top of the kernel address space which
+ * a hypervisor can load into later.  Needed for dynamically loaded hypervisors,
+ * so relocating the fixmap can be done before paging initialization.
+ */
+static int __init parse_reservetop(char *arg)
+{
+	unsigned long address;
+
+	if (!arg)
+		return -EINVAL;
+
+	address = memparse(arg, &arg);
+	reserve_top_address(address);
+	return 0;
+}
+early_param("reservetop", parse_reservetop);
+
+/*
  * Callback for efi_memory_walk.
  */
 static int __init
@@ -1181,7 +1200,7 @@ static unsigned long __init setup_memory(void)
 
 void __init zone_sizes_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
 	unsigned int max_dma, low;
 
 	max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
@@ -1258,7 +1277,7 @@ void __init setup_bootmem_allocator(void)
 	 */
 	find_smp_config();
 #endif
-
+	numa_kva_reserve();
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (LOADER_TYPE && INITRD_START) {
 		if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
index c10789d7a9d..465188e2d70 100644
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -634,3 +634,69 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs)
 	}
 }
 
+/*
+ * this function sends a 'generic call function' IPI to one other CPU
+ * in the system.
+ *
+ * cpu is a standard Linux logical CPU number.
+ */
+static void
+__smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+				int nonatomic, int wait)
+{
+	struct call_data_struct data;
+	int cpus = 1;
+
+	data.func = func;
+	data.info = info;
+	atomic_set(&data.started, 0);
+	data.wait = wait;
+	if (wait)
+		atomic_set(&data.finished, 0);
+
+	call_data = &data;
+	wmb();
+	/* Send a message to all other CPUs and wait for them to respond */
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);
+
+	/* Wait for response */
+	while (atomic_read(&data.started) != cpus)
+		cpu_relax();
+
+	if (!wait)
+		return;
+
+	while (atomic_read(&data.finished) != cpus)
+		cpu_relax();
+}
+
+/*
+ * smp_call_function_single - Run a function on another CPU
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: Currently unused.
+ * @wait: If true, wait until function has completed on other CPUs.
+ *
+ * Retrurns 0 on success, else a negative status code.
+ *
+ * Does not return until the remote CPU is nearly ready to execute <func>
+ * or is or has executed.
+ */
+
+int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+			int nonatomic, int wait)
+{
+	/* prevent preemption and reschedule on another processor */
+	int me = get_cpu();
+	if (cpu == me) {
+		WARN_ON(1);
+		put_cpu();
+		return -EBUSY;
+	}
+	spin_lock_bh(&call_lock);
+	__smp_call_function_single(cpu, func, info, nonatomic, wait);
+	spin_unlock_bh(&call_lock);
+	put_cpu();
+	return 0;
+}
+EXPORT_SYMBOL(smp_call_function_single);
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index f948419c888..efe07990e7f 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -642,9 +642,13 @@ static void map_cpu_to_logical_apicid(void)
 {
 	int cpu = smp_processor_id();
 	int apicid = logical_smp_processor_id();
+	int node = apicid_to_node(apicid);
+
+	if (!node_online(node))
+		node = first_online_node;
 
 	cpu_2_logical_apicid[cpu] = apicid;
-	map_cpu_to_node(cpu, apicid_to_node(apicid));
+	map_cpu_to_node(cpu, node);
 }
 
 static void unmap_cpu_to_logical_apicid(int cpu)
diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c
index b1809c9a089..83db411b3aa 100644
--- a/arch/i386/kernel/srat.c
+++ b/arch/i386/kernel/srat.c
@@ -42,7 +42,7 @@
 #define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8) 
 static u8 pxm_bitmap[PXM_BITMAP_LEN];	/* bitmap of proximity domains */
 
-#define MAX_CHUNKS_PER_NODE	4
+#define MAX_CHUNKS_PER_NODE	3
 #define MAXCHUNKS		(MAX_CHUNKS_PER_NODE * MAX_NUMNODES)
 struct node_memory_chunk_s {
 	unsigned long	start_pfn;
@@ -135,9 +135,6 @@ static void __init parse_memory_affinity_structure (char *sratp)
 		 "enabled and removable" : "enabled" ) );
 }
 
-#if MAX_NR_ZONES != 4
-#error "MAX_NR_ZONES != 4, chunk_to_zone requires review"
-#endif
 /* Take a chunk of pages from page frame cstart to cend and count the number
  * of pages in each zone, returned via zones[].
  */
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index edd00f6cee3..1302e4ab3c4 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -270,16 +270,19 @@ void notify_arch_cmos_timer(void)
 	mod_timer(&sync_cmos_timer, jiffies + 1);
 }
 
-static long clock_cmos_diff, sleep_start;
+static long clock_cmos_diff;
+static unsigned long sleep_start;
 
 static int timer_suspend(struct sys_device *dev, pm_message_t state)
 {
 	/*
 	 * Estimate time zone so that set_time can update the clock
 	 */
-	clock_cmos_diff = -get_cmos_time();
+	unsigned long ctime =  get_cmos_time();
+
+	clock_cmos_diff = -ctime;
 	clock_cmos_diff += get_seconds();
-	sleep_start = get_cmos_time();
+	sleep_start = ctime;
 	return 0;
 }
 
@@ -287,18 +290,29 @@ static int timer_resume(struct sys_device *dev)
 {
 	unsigned long flags;
 	unsigned long sec;
-	unsigned long sleep_length;
-
+	unsigned long ctime = get_cmos_time();
+	long sleep_length = (ctime - sleep_start) * HZ;
+	struct timespec ts;
+
+	if (sleep_length < 0) {
+		printk(KERN_WARNING "CMOS clock skew detected in timer resume!\n");
+		/* The time after the resume must not be earlier than the time
+		 * before the suspend or some nasty things will happen
+		 */
+		sleep_length = 0;
+		ctime = sleep_start;
+	}
 #ifdef CONFIG_HPET_TIMER
 	if (is_hpet_enabled())
 		hpet_reenable();
 #endif
 	setup_pit_timer();
-	sec = get_cmos_time() + clock_cmos_diff;
-	sleep_length = (get_cmos_time() - sleep_start) * HZ;
+
+	sec = ctime + clock_cmos_diff;
+	ts.tv_sec = sec;
+	ts.tv_nsec = 0;
+	do_settimeofday(&ts);
 	write_seqlock_irqsave(&xtime_lock, flags);
-	xtime.tv_sec = sec;
-	xtime.tv_nsec = 0;
 	jiffies_64 += sleep_length;
 	wall_jiffies += sleep_length;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -334,10 +348,11 @@ extern void (*late_time_init)(void);
 /* Duplicate of time_init() below, with hpet_enable part added */
 static void __init hpet_time_init(void)
 {
-	xtime.tv_sec = get_cmos_time();
-	xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
-	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
+	struct timespec ts;
+	ts.tv_sec = get_cmos_time();
+	ts.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
+
+	do_settimeofday(&ts);
 
 	if ((hpet_enable() >= 0) && hpet_use_timer) {
 		printk("Using HPET for base-timer\n");
@@ -349,6 +364,7 @@ static void __init hpet_time_init(void)
 
 void __init time_init(void)
 {
+	struct timespec ts;
 #ifdef CONFIG_HPET_TIMER
 	if (is_hpet_capable()) {
 		/*
@@ -359,10 +375,10 @@ void __init time_init(void)
 		return;
 	}
 #endif
-	xtime.tv_sec = get_cmos_time();
-	xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
-	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
+	ts.tv_sec = get_cmos_time();
+	ts.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
+
+	do_settimeofday(&ts);
 
 	time_init_hook();
 }
diff --git a/arch/i386/kernel/time_hpet.c b/arch/i386/kernel/time_hpet.c
index 14a1376fedd..6bf14a4e995 100644
--- a/arch/i386/kernel/time_hpet.c
+++ b/arch/i386/kernel/time_hpet.c
@@ -301,23 +301,25 @@ int hpet_rtc_timer_init(void)
 		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
 
 	local_irq_save(flags);
+
 	cnt = hpet_readl(HPET_COUNTER);
 	cnt += ((hpet_tick*HZ)/hpet_rtc_int_freq);
 	hpet_writel(cnt, HPET_T1_CMP);
 	hpet_t1_cmp = cnt;
-	local_irq_restore(flags);
 
 	cfg = hpet_readl(HPET_T1_CFG);
 	cfg &= ~HPET_TN_PERIODIC;
 	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
 	hpet_writel(cfg, HPET_T1_CFG);
 
+	local_irq_restore(flags);
+
 	return 1;
 }
 
 static void hpet_rtc_timer_reinit(void)
 {
-	unsigned int cfg, cnt;
+	unsigned int cfg, cnt, ticks_per_int, lost_ints;
 
 	if (unlikely(!(PIE_on | AIE_on | UIE_on))) {
 		cfg = hpet_readl(HPET_T1_CFG);
@@ -332,10 +334,33 @@ static void hpet_rtc_timer_reinit(void)
 		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
 
 	/* It is more accurate to use the comparator value than current count.*/
-	cnt = hpet_t1_cmp;
-	cnt += hpet_tick*HZ/hpet_rtc_int_freq;
-	hpet_writel(cnt, HPET_T1_CMP);
-	hpet_t1_cmp = cnt;
+	ticks_per_int = hpet_tick * HZ / hpet_rtc_int_freq;
+	hpet_t1_cmp += ticks_per_int;
+	hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
+
+	/*
+	 * If the interrupt handler was delayed too long, the write above tries
+	 * to schedule the next interrupt in the past and the hardware would
+	 * not interrupt until the counter had wrapped around.
+	 * So we have to check that the comparator wasn't set to a past time.
+	 */
+	cnt = hpet_readl(HPET_COUNTER);
+	if (unlikely((int)(cnt - hpet_t1_cmp) > 0)) {
+		lost_ints = (cnt - hpet_t1_cmp) / ticks_per_int + 1;
+		/* Make sure that, even with the time needed to execute
+		 * this code, the next scheduled interrupt has been moved
+		 * back to the future: */
+		lost_ints++;
+
+		hpet_t1_cmp += lost_ints * ticks_per_int;
+		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
+
+		if (PIE_on)
+			PIE_count += lost_ints;
+
+		printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
+		       hpet_rtc_int_freq);
+	}
 }
 
 /*
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 7e9edafffd8..4fcc6690be9 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -313,6 +313,8 @@ void show_registers(struct pt_regs *regs)
 	 */
 	if (in_kernel) {
 		u8 __user *eip;
+		int code_bytes = 64;
+		unsigned char c;
 
 		printk("\n" KERN_EMERG "Stack: ");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)esp, KERN_EMERG);
@@ -320,9 +322,12 @@ void show_registers(struct pt_regs *regs)
 		printk(KERN_EMERG "Code: ");
 
 		eip = (u8 __user *)regs->eip - 43;
-		for (i = 0; i < 64; i++, eip++) {
-			unsigned char c;
-
+		if (eip < (u8 __user *)PAGE_OFFSET || __get_user(c, eip)) {
+			/* try starting at EIP */
+			eip = (u8 __user *)regs->eip;
+			code_bytes = 32;
+		}
+		for (i = 0; i < code_bytes; i++, eip++) {
 			if (eip < (u8 __user *)PAGE_OFFSET || __get_user(c, eip)) {
 				printk(" Bad EIP value.");
 				break;
diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index 2d4f1386e2b..1e7ac1c44dd 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -13,6 +13,12 @@ OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
 OUTPUT_ARCH(i386)
 ENTRY(phys_startup_32)
 jiffies = jiffies_64;
+
+PHDRS {
+	text PT_LOAD FLAGS(5);	/* R_E */
+	data PT_LOAD FLAGS(7);	/* RWE */
+	note PT_NOTE FLAGS(4);	/* R__ */
+}
 SECTIONS
 {
   . = __KERNEL_START;
@@ -26,7 +32,7 @@ SECTIONS
 	KPROBES_TEXT
 	*(.fixup)
 	*(.gnu.warning)
-	} = 0x9090
+	} :text = 0x9090
 
   _etext = .;			/* End of text section */
 
@@ -48,7 +54,7 @@ SECTIONS
   .data : AT(ADDR(.data) - LOAD_OFFSET) {	/* Data */
 	*(.data)
 	CONSTRUCTORS
-	}
+	} :data
 
   . = ALIGN(4096);
   __nosave_begin = .;
@@ -184,4 +190,6 @@ SECTIONS
   STABS_DEBUG
 
   DWARF_DEBUG
+
+  NOTES
 }
diff --git a/arch/i386/mach-voyager/voyager_thread.c b/arch/i386/mach-voyager/voyager_thread.c
index 50f6de6ff64..f39887359e8 100644
--- a/arch/i386/mach-voyager/voyager_thread.c
+++ b/arch/i386/mach-voyager/voyager_thread.c
@@ -130,7 +130,6 @@ thread(void *unused)
 	init_timer(&wakeup_timer);
 
 	sigfillset(&current->blocked);
-	current->signal->tty = NULL;
 
 	printk(KERN_NOTICE "Voyager starting monitor thread\n");
 
diff --git a/arch/i386/mm/boot_ioremap.c b/arch/i386/mm/boot_ioremap.c
index 5d44f4f5ff5..4de11f508c3 100644
--- a/arch/i386/mm/boot_ioremap.c
+++ b/arch/i386/mm/boot_ioremap.c
@@ -29,8 +29,11 @@
  */
 
 #define BOOT_PTE_PTRS (PTRS_PER_PTE*2)
-#define boot_pte_index(address) \
-	     (((address) >> PAGE_SHIFT) & (BOOT_PTE_PTRS - 1))
+
+static unsigned long boot_pte_index(unsigned long vaddr) 
+{
+	return __pa(vaddr) >> PAGE_SHIFT;
+}
 
 static inline boot_pte_t* boot_vaddr_to_pte(void *address)
 {
diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c
index 7c392dc553b..fb5d8b747de 100644
--- a/arch/i386/mm/discontig.c
+++ b/arch/i386/mm/discontig.c
@@ -117,7 +117,8 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 void *node_remap_end_vaddr[MAX_NUMNODES];
 void *node_remap_alloc_vaddr[MAX_NUMNODES];
-
+static unsigned long kva_start_pfn;
+static unsigned long kva_pages;
 /*
  * FLAT - support for basic PC memory model with discontig enabled, essentially
  *        a single node with all available processors in it with a flat
@@ -286,7 +287,6 @@ unsigned long __init setup_memory(void)
 {
 	int nid;
 	unsigned long system_start_pfn, system_max_low_pfn;
-	unsigned long reserve_pages;
 
 	/*
 	 * When mapping a NUMA machine we allocate the node_mem_map arrays
@@ -298,14 +298,23 @@ unsigned long __init setup_memory(void)
 	find_max_pfn();
 	get_memcfg_numa();
 
-	reserve_pages = calculate_numa_remap_pages();
+	kva_pages = calculate_numa_remap_pages();
 
 	/* partially used pages are not usable - thus round upwards */
 	system_start_pfn = min_low_pfn = PFN_UP(init_pg_tables_end);
 
-	system_max_low_pfn = max_low_pfn = find_max_low_pfn() - reserve_pages;
-	printk("reserve_pages = %ld find_max_low_pfn() ~ %ld\n",
-			reserve_pages, max_low_pfn + reserve_pages);
+	kva_start_pfn = find_max_low_pfn() - kva_pages;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	/* Numa kva area is below the initrd */
+	if (LOADER_TYPE && INITRD_START)
+		kva_start_pfn = PFN_DOWN(INITRD_START)  - kva_pages;
+#endif
+	kva_start_pfn -= kva_start_pfn & (PTRS_PER_PTE-1);
+
+	system_max_low_pfn = max_low_pfn = find_max_low_pfn();
+	printk("kva_start_pfn ~ %ld find_max_low_pfn() ~ %ld\n",
+		kva_start_pfn, max_low_pfn);
 	printk("max_pfn = %ld\n", max_pfn);
 #ifdef CONFIG_HIGHMEM
 	highstart_pfn = highend_pfn = max_pfn;
@@ -323,7 +332,7 @@ unsigned long __init setup_memory(void)
 			(ulong) pfn_to_kaddr(max_low_pfn));
 	for_each_online_node(nid) {
 		node_remap_start_vaddr[nid] = pfn_to_kaddr(
-				highstart_pfn + node_remap_offset[nid]);
+				kva_start_pfn + node_remap_offset[nid]);
 		/* Init the node remap allocator */
 		node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +
 			(node_remap_size[nid] * PAGE_SIZE);
@@ -338,7 +347,6 @@ unsigned long __init setup_memory(void)
 	}
 	printk("High memory starts at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(highstart_pfn));
-	vmalloc_earlyreserve = reserve_pages * PAGE_SIZE;
 	for_each_online_node(nid)
 		find_max_pfn_node(nid);
 
@@ -348,13 +356,18 @@ unsigned long __init setup_memory(void)
 	return max_low_pfn;
 }
 
+void __init numa_kva_reserve(void)
+{
+	reserve_bootmem(PFN_PHYS(kva_start_pfn),PFN_PHYS(kva_pages));
+}
+
 void __init zone_sizes_init(void)
 {
 	int nid;
 
 
 	for_each_online_node(nid) {
-		unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
+		unsigned long zones_size[MAX_NR_ZONES] = {0, };
 		unsigned long *zholes_size;
 		unsigned int max_dma;
 
@@ -409,7 +422,7 @@ void __init set_highmem_pages_init(int bad_ppro)
 		zone_end_pfn = zone_start_pfn + zone->spanned_pages;
 
 		printk("Initializing %s for node %d (%08lx:%08lx)\n",
-				zone->name, zone->zone_pgdat->node_id,
+				zone->name, zone_to_nid(zone),
 				zone_start_pfn, zone_end_pfn);
 
 		for (node_pfn = zone_start_pfn; node_pfn < zone_end_pfn; node_pfn++) {
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 89e8486aac3..efd0bcdac65 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -629,6 +629,48 @@ void __init mem_init(void)
 		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
 	       );
 
+#if 1 /* double-sanity-check paranoia */
+	printk("virtual kernel memory layout:\n"
+	       "    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+#ifdef CONFIG_HIGHMEM
+	       "    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+#endif
+	       "    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+	       "    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+	       "      .init : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+	       "      .data : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+	       "      .text : 0x%08lx - 0x%08lx   (%4ld kB)\n",
+	       FIXADDR_START, FIXADDR_TOP,
+	       (FIXADDR_TOP - FIXADDR_START) >> 10,
+
+#ifdef CONFIG_HIGHMEM
+	       PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
+	       (LAST_PKMAP*PAGE_SIZE) >> 10,
+#endif
+
+	       VMALLOC_START, VMALLOC_END,
+	       (VMALLOC_END - VMALLOC_START) >> 20,
+
+	       (unsigned long)__va(0), (unsigned long)high_memory,
+	       ((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,
+
+	       (unsigned long)&__init_begin, (unsigned long)&__init_end,
+	       ((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10,
+
+	       (unsigned long)&_etext, (unsigned long)&_edata,
+	       ((unsigned long)&_edata - (unsigned long)&_etext) >> 10,
+
+	       (unsigned long)&_text, (unsigned long)&_etext,
+	       ((unsigned long)&_etext - (unsigned long)&_text) >> 10);
+
+#ifdef CONFIG_HIGHMEM
+	BUG_ON(PKMAP_BASE+LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
+	BUG_ON(VMALLOC_END                     > PKMAP_BASE);
+#endif
+	BUG_ON(VMALLOC_START                   > VMALLOC_END);
+	BUG_ON((unsigned long)high_memory      > VMALLOC_START);
+#endif /* double-sanity-check paranoia */
+
 #ifdef CONFIG_X86_PAE
 	if (!cpu_has_pae)
 		panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!");
@@ -657,7 +699,7 @@ void __init mem_init(void)
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdata = &contig_page_data;
-	struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
+	struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index bd98768d876..10126e3f817 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
+#include <linux/module.h>
 
 #include <asm/system.h>
 #include <asm/pgtable.h>
@@ -60,7 +61,9 @@ void show_mem(void)
 	printk(KERN_INFO "%lu pages writeback\n",
 					global_page_state(NR_WRITEBACK));
 	printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-	printk(KERN_INFO "%lu pages slab\n", global_page_state(NR_SLAB));
+	printk(KERN_INFO "%lu pages slab\n",
+		global_page_state(NR_SLAB_RECLAIMABLE) +
+		global_page_state(NR_SLAB_UNRECLAIMABLE));
 	printk(KERN_INFO "%lu pages pagetables\n",
 					global_page_state(NR_PAGETABLE));
 }
@@ -137,6 +140,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 	__flush_tlb_one(vaddr);
 }
 
+static int fixmaps;
+#ifndef CONFIG_COMPAT_VDSO
+unsigned long __FIXADDR_TOP = 0xfffff000;
+EXPORT_SYMBOL(__FIXADDR_TOP);
+#endif
+
 void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
 {
 	unsigned long address = __fix_to_virt(idx);
@@ -146,6 +155,25 @@ void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
 		return;
 	}
 	set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
+	fixmaps++;
+}
+
+/**
+ * reserve_top_address - reserves a hole in the top of kernel address space
+ * @reserve - size of hole to reserve
+ *
+ * Can be used to relocate the fixmap area and poke a hole in the top
+ * of kernel address space to make room for a hypervisor.
+ */
+void reserve_top_address(unsigned long reserve)
+{
+	BUG_ON(fixmaps > 0);
+#ifdef CONFIG_COMPAT_VDSO
+	BUG_ON(reserve != 0);
+#else
+	__FIXADDR_TOP = -reserve - PAGE_SIZE;
+	__VMALLOC_RESERVE += reserve;
+#endif
 }
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
diff --git a/arch/i386/power/swsusp.S b/arch/i386/power/swsusp.S
index c893b897217..8a2b50a0aaa 100644
--- a/arch/i386/power/swsusp.S
+++ b/arch/i386/power/swsusp.S
@@ -32,7 +32,7 @@ ENTRY(swsusp_arch_resume)
 	movl	$swsusp_pg_dir-__PAGE_OFFSET, %ecx
 	movl	%ecx, %cr3
 
-	movl	pagedir_nosave, %edx
+	movl	restore_pblist, %edx
 	.p2align 4,,7
 
 copy_loop: