Merge branch 'master' into gfs2

14 files changed, 187 insertions, 242 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index 32ae1378f35c..b87a19f0d584 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -367,6 +367,10 @@ config ARCH_FLATMEM_ENABLE
 
 source "mm/Kconfig"
 
+config MEMORY_HOTPLUG_RESERVE
+	def_bool y
+	depends on (MEMORY_HOTPLUG && DISCONTIGMEM)
+
 config HAVE_ARCH_EARLY_PFN_TO_NID
 	def_bool y
 	depends on NUMA
diff --git a/arch/x86_64/defconfig b/arch/x86_64/defconfig
index 647610ecb580..4844b543bed0 100644
--- a/arch/x86_64/defconfig
+++ b/arch/x86_64/defconfig
@@ -1,11 +1,12 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18-git5
-# Tue Sep 26 09:30:47 2006
+# Linux kernel version: 2.6.18-git7
+# Wed Sep 27 21:53:10 2006
 #
 CONFIG_X86_64=y
 CONFIG_64BIT=y
 CONFIG_X86=y
+CONFIG_ZONE_DMA32=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_SEMAPHORE_SLEEPERS=y
@@ -179,6 +180,7 @@ CONFIG_GENERIC_PENDING_IRQ=y
 CONFIG_PM=y
 # CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
+# CONFIG_PM_SYSFS_DEPRECATED is not set
 CONFIG_SOFTWARE_SUSPEND=y
 CONFIG_PM_STD_PARTITION=""
 CONFIG_SUSPEND_SMP=y
@@ -251,6 +253,7 @@ CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_MSI=y
+# CONFIG_PCI_MULTITHREAD_PROBE is not set
 # CONFIG_PCI_DEBUG is not set
 
 #
@@ -1458,6 +1461,7 @@ CONFIG_KPROBES=y
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_UNUSED_SYMBOLS=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/x86_64/kernel/mpparse.c b/arch/x86_64/kernel/mpparse.c
index 20e88f4b564b..b8d53dfa9931 100644
--- a/arch/x86_64/kernel/mpparse.c
+++ b/arch/x86_64/kernel/mpparse.c
@@ -152,6 +152,21 @@ static void __init MP_bus_info (struct mpc_config_bus *m)
 	}
 }
 
+static int bad_ioapic(unsigned long address)
+{
+	if (nr_ioapics >= MAX_IO_APICS) {
+		printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
+			"(found %d)\n", MAX_IO_APICS, nr_ioapics);
+		panic("Recompile kernel with bigger MAX_IO_APICS!\n");
+	}
+	if (!address) {
+		printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
+			" found in table, skipping!\n");
+		return 1;
+	}
+	return 0;
+}
+
 static void __init MP_ioapic_info (struct mpc_config_ioapic *m)
 {
 	if (!(m->mpc_flags & MPC_APIC_USABLE))
@@ -159,16 +174,10 @@ static void __init MP_ioapic_info (struct mpc_config_ioapic *m)
 
 	printk("I/O APIC #%d at 0x%X.\n",
 		m->mpc_apicid, m->mpc_apicaddr);
-	if (nr_ioapics >= MAX_IO_APICS) {
-		printk(KERN_ERR "Max # of I/O APICs (%d) exceeded (found %d).\n",
-			MAX_IO_APICS, nr_ioapics);
-		panic("Recompile kernel with bigger MAX_IO_APICS!.\n");
-	}
-	if (!m->mpc_apicaddr) {
-		printk(KERN_ERR "WARNING: bogus zero I/O APIC address"
-			" found in MP table, skipping!\n");
+
+	if (bad_ioapic(m->mpc_apicaddr))
 		return;
-	}
+
 	mp_ioapics[nr_ioapics] = *m;
 	nr_ioapics++;
 }
@@ -647,16 +656,8 @@ void __init mp_register_ioapic(u8 id, u32 address, u32 gsi_base)
 {
 	int idx = 0;
 
-	if (nr_ioapics >= MAX_IO_APICS) {
-		printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
-			"(found %d)\n", MAX_IO_APICS, nr_ioapics);
-		panic("Recompile kernel with bigger MAX_IO_APICS!\n");
-	}
-	if (!address) {
-		printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address"
-			" found in MADT table, skipping!\n");
+	if (bad_ioapic(address))
 		return;
-	}
 
 	idx = nr_ioapics++;
 
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 4d6fb047952e..7af9cb3e2d99 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -28,6 +28,10 @@
 #include <asm/mce.h>
 #include <asm/intel_arch_perfmon.h>
 
+int unknown_nmi_panic;
+int nmi_watchdog_enabled;
+int panic_on_unrecovered_nmi;
+
 /* perfctr_nmi_owner tracks the ownership of the perfctr registers:
  * evtsel_nmi_owner tracks the ownership of the event selection
  * - different performance counters/ event selection may be reserved for
diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c
index 4dcb671bd19f..f8d857453f8a 100644
--- a/arch/x86_64/kernel/pci-dma.c
+++ b/arch/x86_64/kernel/pci-dma.c
@@ -170,8 +170,20 @@ void dma_free_coherent(struct device *dev, size_t size,
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
+static int forbid_dac __read_mostly;
+
 int dma_supported(struct device *dev, u64 mask)
 {
+#ifdef CONFIG_PCI
+	if (mask > 0xffffffff && forbid_dac > 0) {
+
+
+
+		printk(KERN_INFO "PCI: Disallowing DAC for device %s\n", dev->bus_id);
+		return 0;
+	}
+#endif
+
 	if (dma_ops->dma_supported)
 		return dma_ops->dma_supported(dev, mask);
 
@@ -231,57 +243,64 @@ EXPORT_SYMBOL(dma_set_mask);
    allowed  overwrite iommu off workarounds for specific chipsets.
    soft	 Use software bounce buffering (default for Intel machines)
    noaperture Don't touch the aperture for AGP.
+   allowdac Allow DMA >4GB
+   nodac    Forbid DMA >4GB
+   panic    Force panic when IOMMU overflows
 */
 __init int iommu_setup(char *p)
 {
-    iommu_merge = 1;
+	iommu_merge = 1;
 
 	if (!p)
 		return -EINVAL;
 
-    while (*p) {
-	    if (!strncmp(p,"off",3))
-		    no_iommu = 1;
-	    /* gart_parse_options has more force support */
-	    if (!strncmp(p,"force",5))
-		    force_iommu = 1;
-	    if (!strncmp(p,"noforce",7)) {
-		    iommu_merge = 0;
-		    force_iommu = 0;
-	    }
-
-	    if (!strncmp(p, "biomerge",8)) {
-		    iommu_bio_merge = 4096;
-		    iommu_merge = 1;
-		    force_iommu = 1;
-	    }
-	    if (!strncmp(p, "panic",5))
-		    panic_on_overflow = 1;
-	    if (!strncmp(p, "nopanic",7))
-		    panic_on_overflow = 0;
-	    if (!strncmp(p, "merge",5)) {
-		    iommu_merge = 1;
-		    force_iommu = 1;
-	    }
-	    if (!strncmp(p, "nomerge",7))
-		    iommu_merge = 0;
-	    if (!strncmp(p, "forcesac",8))
-		    iommu_sac_force = 1;
+	while (*p) {
+		if (!strncmp(p,"off",3))
+			no_iommu = 1;
+		/* gart_parse_options has more force support */
+		if (!strncmp(p,"force",5))
+			force_iommu = 1;
+		if (!strncmp(p,"noforce",7)) {
+			iommu_merge = 0;
+			force_iommu = 0;
+		}
+
+		if (!strncmp(p, "biomerge",8)) {
+			iommu_bio_merge = 4096;
+			iommu_merge = 1;
+			force_iommu = 1;
+		}
+		if (!strncmp(p, "panic",5))
+			panic_on_overflow = 1;
+		if (!strncmp(p, "nopanic",7))
+			panic_on_overflow = 0;
+		if (!strncmp(p, "merge",5)) {
+			iommu_merge = 1;
+			force_iommu = 1;
+		}
+		if (!strncmp(p, "nomerge",7))
+			iommu_merge = 0;
+		if (!strncmp(p, "forcesac",8))
+			iommu_sac_force = 1;
+		if (!strncmp(p, "allowdac", 8))
+			forbid_dac = 0;
+		if (!strncmp(p, "nodac", 5))
+			forbid_dac = -1;
 
 #ifdef CONFIG_SWIOTLB
-	    if (!strncmp(p, "soft",4))
-		    swiotlb = 1;
+		if (!strncmp(p, "soft",4))
+			swiotlb = 1;
 #endif
 
 #ifdef CONFIG_IOMMU
-	    gart_parse_options(p);
+		gart_parse_options(p);
 #endif
 
-	    p += strcspn(p, ",");
-	    if (*p == ',')
-		    ++p;
-    }
-    return 0;
+		p += strcspn(p, ",");
+		if (*p == ',')
+			++p;
+	}
+	return 0;
 }
 early_param("iommu", iommu_setup);
 
diff --git a/arch/x86_64/kernel/pci-swiotlb.c b/arch/x86_64/kernel/pci-swiotlb.c
index 6a55f87ba97f..697f0aa794b9 100644
--- a/arch/x86_64/kernel/pci-swiotlb.c
+++ b/arch/x86_64/kernel/pci-swiotlb.c
@@ -3,7 +3,8 @@
 #include <linux/pci.h>
 #include <linux/cache.h>
 #include <linux/module.h>
-#include <asm/dma-mapping.h>
+#include <linux/dma-mapping.h>
+
 #include <asm/proto.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 0b00bb2ea576..fc944b5e8f4a 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -123,9 +123,6 @@ struct resource standard_io_resources[] = {
 		.flags = IORESOURCE_BUSY | IORESOURCE_IO }
 };
 
-#define STANDARD_IO_RESOURCES \
-	(sizeof standard_io_resources / sizeof standard_io_resources[0])
-
 #define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM)
 
 struct resource data_resource = {
@@ -172,9 +169,6 @@ static struct resource adapter_rom_resources[] = {
 		.flags = IORESOURCE_ROM }
 };
 
-#define ADAPTER_ROM_RESOURCES \
-	(sizeof adapter_rom_resources / sizeof adapter_rom_resources[0])
-
 static struct resource video_rom_resource = {
 	.name = "Video ROM",
 	.start = 0xc0000,
@@ -245,7 +239,8 @@ static void __init probe_roms(void)
 	}
 
 	/* check for adapter roms on 2k boundaries */
-	for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) {
+	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper;
+	     start += 2048) {
 		rom = isa_bus_to_virt(start);
 		if (!romsignature(rom))
 			continue;
@@ -537,7 +532,7 @@ void __init setup_arch(char **cmdline_p)
 	{
 	unsigned i;
 	/* request I/O space for devices used on all i[345]86 PCs */
-	for (i = 0; i < STANDARD_IO_RESOURCES; i++)
+	for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
 		request_resource(&ioport_resource, &standard_io_resources[i]);
 	}
 
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 1c255ee76e7c..557e92af7bea 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -77,7 +77,6 @@ unsigned long long monotonic_base;
 struct vxtime_data __vxtime __section_vxtime;	/* for vsyscalls */
 
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
-unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES;
 struct timespec __xtime __section_xtime;
 struct timezone __sys_tz __section_sys_tz;
 
@@ -119,7 +118,7 @@ unsigned int (*do_gettimeoffset)(void) = do_gettimeoffset_tsc;
 
 void do_gettimeofday(struct timeval *tv)
 {
-	unsigned long seq, t;
+	unsigned long seq;
  	unsigned int sec, usec;
 
 	do {
@@ -136,10 +135,7 @@ void do_gettimeofday(struct timeval *tv)
 		   be found. Note when you fix it here you need to do the same
 		   in arch/x86_64/kernel/vsyscall.c and export all needed
 		   variables in vmlinux.lds. -AK */ 
-
-		t = (jiffies - wall_jiffies) * USEC_PER_TICK +
-			do_gettimeoffset();
-		usec += t;
+		usec += do_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -165,8 +161,7 @@ int do_settimeofday(struct timespec *tv)
 
 	write_seqlock_irq(&xtime_lock);
 
-	nsec -= do_gettimeoffset() * NSEC_PER_USEC +
-		(jiffies - wall_jiffies) * NSEC_PER_TICK;
+	nsec -= do_gettimeoffset() * NSEC_PER_USEC;
 
 	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
 	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
@@ -415,16 +410,16 @@ void main_timer_handler(struct pt_regs *regs)
 				(((long) offset << US_SCALE) / vxtime.tsc_quot) - 1;
 	}
 
-	if (lost > 0) {
+	if (lost > 0)
 		handle_lost_ticks(lost, regs);
-		jiffies += lost;
-	}
+	else
+		lost = 0;
 
 /*
  * Do the timer stuff.
  */
 
-	do_timer(regs);
+	do_timer(lost + 1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode(regs));
 #endif
@@ -1071,7 +1066,6 @@ static int timer_resume(struct sys_device *dev)
 		vxtime.last_tsc = get_cycles_sync();
 	write_sequnlock_irqrestore(&xtime_lock,flags);
 	jiffies += sleep_length;
-	wall_jiffies += sleep_length;
 	monotonic_base += sleep_length * (NSEC_PER_SEC/HZ);
 	touch_softlockup_watchdog();
 	return 0;
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index d0564f1bcb0b..b9df2ab6529f 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -67,13 +67,6 @@ SECTIONS
 
   _edata = .;			/* End of data section */
 
-  __bss_start = .;		/* BSS */
-  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
-	*(.bss.page_aligned)	
-	*(.bss)
-	}
-  __bss_stop = .;
-
   . = ALIGN(PAGE_SIZE);
   . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
   .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
@@ -108,9 +101,6 @@ SECTIONS
   .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { *(.vgetcpu_mode) }
   vgetcpu_mode = VVIRT(.vgetcpu_mode);
 
-  .wall_jiffies : AT(VLOAD(.wall_jiffies)) { *(.wall_jiffies) }
-  wall_jiffies = VVIRT(.wall_jiffies);
-
   .sys_tz : AT(VLOAD(.sys_tz)) { *(.sys_tz) }
   sys_tz = VVIRT(.sys_tz);
 
@@ -229,6 +219,13 @@ SECTIONS
   . = ALIGN(4096);
   __nosave_end = .;
 
+  __bss_start = .;		/* BSS */
+  .bss : AT(ADDR(.bss) - LOAD_OFFSET) {
+	*(.bss.page_aligned)
+	*(.bss)
+	}
+  __bss_stop = .;
+
   _end = . ;
 
   /* Sections to be discarded */
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index ac48c3857ddb..a98b460af6a1 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -66,8 +66,7 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 		sequence = read_seqbegin(&__xtime_lock);
 		
 		sec = __xtime.tv_sec;
-		usec = (__xtime.tv_nsec / 1000) +
-			(__jiffies - __wall_jiffies) * (1000000 / HZ);
+		usec = __xtime.tv_nsec / 1000;
 
 		if (__vxtime.mode != VXTIME_HPET) {
 			t = get_cycles_sync();
@@ -155,8 +154,8 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 	   We do this here because otherwise user space would do it on
 	   its own in a likely inferior way (no access to jiffies).
 	   If you don't like it pass NULL. */
-	if (tcache && tcache->t0 == (j = __jiffies)) {
-		p = tcache->t1;
+	if (tcache && tcache->blob[0] == (j = __jiffies)) {
+		p = tcache->blob[1];
 	} else if (__vgetcpu_mode == VGETCPU_RDTSCP) {
 		/* Load per CPU data from RDTSCP */
 		rdtscp(dummy, dummy, p);
@@ -165,8 +164,8 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
 		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 	if (tcache) {
-		tcache->t0 = j;
-		tcache->t1 = p;
+		tcache->blob[0] = j;
+		tcache->blob[1] = p;
 	}
 	if (cpu)
 		*cpu = p & 0xfff;
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 1a17b0733ab5..3751b4788e28 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -244,7 +244,7 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
-	if (tsk->pid == 1)
+	if (is_init(tsk))
 		return 1;
 	if (tsk->ptrace & PT_PTRACED)
 		return 0;
@@ -464,7 +464,7 @@ good_area:
 		case PF_PROT:		/* read, present */
 			goto bad_area;
 		case 0:			/* read, not present */
-			if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 				goto bad_area;
 	}
 
@@ -580,7 +580,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) { 
+	if (is_init(current)) {
 		yield();
 		goto again;
 	}
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 3e16fe08150e..19c72520a868 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -463,19 +463,6 @@ void online_page(struct page *page)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * XXX: memory_add_physaddr_to_nid() is to find node id from physical address
- *	via probe interface of sysfs. If acpi notifies hot-add event, then it
- *	can tell node id by searching dsdt. But, probe interface doesn't have
- *	node id. So, return 0 as node id at this time.
- */
-#ifdef CONFIG_NUMA
-int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-#endif
-
-/*
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
@@ -487,12 +474,12 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
+	init_memory_mapping(start, (start + size -1));
+
 	ret = __add_pages(zone, start_pfn, nr_pages);
 	if (ret)
 		goto error;
 
-	init_memory_mapping(start, (start + size -1));
-
 	return ret;
 error:
 	printk("%s: Problem encountered in __add_pages!\n", __func__);
@@ -506,7 +493,24 @@ int remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
-#else /* CONFIG_MEMORY_HOTPLUG */
+#ifndef CONFIG_ACPI_NUMA
+int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
+#ifndef CONFIG_ACPI_NUMA
+int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+#endif
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
 /*
  * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
  * just online the pages.
@@ -532,7 +536,7 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
 	}
 	return err;
 }
-#endif /* CONFIG_MEMORY_HOTPLUG */
+#endif
 
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
 			 kcore_vsyscall;
diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c
index 45d7d823c3b8..c6e5e8d401a4 100644
--- a/arch/x86_64/mm/ioremap.c
+++ b/arch/x86_64/mm/ioremap.c
@@ -12,117 +12,16 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
-#include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 #include <asm/proto.h>
 
 #define ISA_START_ADDRESS      0xa0000
 #define ISA_END_ADDRESS                0x100000
 
-static inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size,
-	unsigned long phys_addr, unsigned long flags)
-{
-	unsigned long end;
-	unsigned long pfn;
-
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	if (address >= end)
-		BUG();
-	pfn = phys_addr >> PAGE_SHIFT;
-	do {
-		if (!pte_none(*pte)) {
-			printk("remap_area_pte: page already exists\n");
-			BUG();
-		}
-		set_pte(pte, pfn_pte(pfn, __pgprot(_PAGE_PRESENT | _PAGE_RW | 
-					_PAGE_GLOBAL | _PAGE_DIRTY | _PAGE_ACCESSED | flags)));
-		address += PAGE_SIZE;
-		pfn++;
-		pte++;
-	} while (address && (address < end));
-}
-
-static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size,
-	unsigned long phys_addr, unsigned long flags)
-{
-	unsigned long end;
-
-	address &= ~PUD_MASK;
-	end = address + size;
-	if (end > PUD_SIZE)
-		end = PUD_SIZE;
-	phys_addr -= address;
-	if (address >= end)
-		BUG();
-	do {
-		pte_t * pte = pte_alloc_kernel(pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		remap_area_pte(pte, address, end - address, address + phys_addr, flags);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address && (address < end));
-	return 0;
-}
-
-static inline int remap_area_pud(pud_t * pud, unsigned long address, unsigned long size,
-	unsigned long phys_addr, unsigned long flags)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	phys_addr -= address;
-	if (address >= end)
-		BUG();
-	do {
-		pmd_t * pmd = pmd_alloc(&init_mm, pud, address);
-		if (!pmd)
-			return -ENOMEM;
-		remap_area_pmd(pmd, address, end - address, address + phys_addr, flags);
-		address = (address + PUD_SIZE) & PUD_MASK;
-		pud++;
-	} while (address && (address < end));
-	return 0;
-}
-
-static int remap_area_pages(unsigned long address, unsigned long phys_addr,
-				 unsigned long size, unsigned long flags)
-{
-	int error;
-	pgd_t *pgd;
-	unsigned long end = address + size;
-
-	phys_addr -= address;
-	pgd = pgd_offset_k(address);
-	flush_cache_all();
-	if (address >= end)
-		BUG();
-	do {
-		pud_t *pud;
-		pud = pud_alloc(&init_mm, pgd, address);
-		error = -ENOMEM;
-		if (!pud)
-			break;
-		if (remap_area_pud(pud, address, end - address,
-					 phys_addr + address, flags))
-			break;
-		error = 0;
-		address = (address + PGDIR_SIZE) & PGDIR_MASK;
-		pgd++;
-	} while (address && (address < end));
-	flush_tlb_all();
-	return error;
-}
-
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
@@ -165,6 +64,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	void * addr;
 	struct vm_struct * area;
 	unsigned long offset, last_addr;
+	pgprot_t pgprot;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -194,6 +94,8 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	}
 #endif
 
+	pgprot = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_GLOBAL
+			  | _PAGE_DIRTY | _PAGE_ACCESSED | flags);
 	/*
 	 * Mappings have to be page-aligned
 	 */
@@ -209,7 +111,8 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 		return NULL;
 	area->phys_addr = phys_addr;
 	addr = area->addr;
-	if (remap_area_pages((unsigned long) addr, phys_addr, size, flags)) {
+	if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
+			       phys_addr, pgprot)) {
 		remove_vm_area((void *)(PAGE_MASK & (unsigned long) addr));
 		return NULL;
 	}
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index f8c04d6935c9..3cc0544e25f5 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -23,22 +23,13 @@
 
 int acpi_numa __initdata;
 
-#if (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \
-	defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) \
-		&& !defined(CONFIG_MEMORY_HOTPLUG)
-#define RESERVE_HOTADD 1
-#endif
-
 static struct acpi_table_slit *acpi_slit;
 
 static nodemask_t nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
-static struct bootnode nodes_add[MAX_NUMNODES] __initdata;
+static struct bootnode nodes_add[MAX_NUMNODES];
 static int found_add_area __initdata;
 int hotadd_percent __initdata = 0;
-#ifndef RESERVE_HOTADD
-#define hotadd_percent 0	/* Ignore all settings */
-#endif
 
 /* Too small nodes confuse the VM badly. Usually they result
    from BIOS bugs. */
@@ -160,7 +151,7 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa)
 	       pxm, pa->apic_id, node);
 }
 
-#ifdef RESERVE_HOTADD
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
 /*
  * Protect against too large hotadd areas that would fill up memory.
  */
@@ -203,15 +194,37 @@ static int hotadd_enough_memory(struct bootnode *nd)
 	return 1;
 }
 
+static int update_end_of_memory(unsigned long end)
+{
+	found_add_area = 1;
+	if ((end >> PAGE_SHIFT) > end_pfn)
+		end_pfn = end >> PAGE_SHIFT;
+	return 1;
+}
+
+static inline int save_add_info(void)
+{
+	return hotadd_percent > 0;
+}
+#else
+int update_end_of_memory(unsigned long end) {return 0;}
+static int hotadd_enough_memory(struct bootnode *nd) {return 1;}
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+static inline int save_add_info(void) {return 1;}
+#else
+static inline int save_add_info(void) {return 0;}
+#endif
+#endif
 /*
- * It is fine to add this area to the nodes data it will be used later
+ * Update nodes_add and decide if to include add are in the zone.
+ * Both SPARSE and RESERVE need nodes_add infomation.
  * This code supports one contigious hot add area per node.
  */
 static int reserve_hotadd(int node, unsigned long start, unsigned long end)
 {
 	unsigned long s_pfn = start >> PAGE_SHIFT;
 	unsigned long e_pfn = end >> PAGE_SHIFT;
-	int changed = 0;
+	int ret = 0, changed = 0;
 	struct bootnode *nd = &nodes_add[node];
 
 	/* I had some trouble with strange memory hotadd regions breaking
@@ -240,7 +253,6 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end)
 
 	/* Looks good */
 
- 	found_add_area = 1;
 	if (nd->start == nd->end) {
  		nd->start = start;
  		nd->end = end;
@@ -258,14 +270,12 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end)
 			printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n");
  	}
 
- 	if ((nd->end >> PAGE_SHIFT) > end_pfn)
- 		end_pfn = nd->end >> PAGE_SHIFT;
+	ret = update_end_of_memory(nd->end);
 
 	if (changed)
 	 	printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end);
-	return 0;
+	return ret;
 }
-#endif
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
 void __init
@@ -284,7 +294,7 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
 	}
 	if (ma->flags.enabled == 0)
 		return;
- 	if (ma->flags.hot_pluggable && hotadd_percent == 0)
+ 	if (ma->flags.hot_pluggable && !save_add_info())
 		return;
 	start = ma->base_addr_lo | ((u64)ma->base_addr_hi << 32);
 	end = start + (ma->length_lo | ((u64)ma->length_hi << 32));
@@ -327,15 +337,13 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
 	push_node_boundaries(node, nd->start >> PAGE_SHIFT,
 						nd->end >> PAGE_SHIFT);
 
-#ifdef RESERVE_HOTADD
- 	if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) {
+ 	if (ma->flags.hot_pluggable && !reserve_hotadd(node, start, end) < 0) {
 		/* Ignore hotadd region. Undo damage */
 		printk(KERN_NOTICE "SRAT: Hotplug region ignored\n");
 		*nd = oldnode;
 		if ((nd->start | nd->end) == 0)
 			node_clear(node, nodes_parsed);
 	}
-#endif
 }
 
 /* Sanity check to catch more bad SRATs (they are amazingly common).
@@ -351,7 +359,6 @@ static int nodes_cover_memory(void)
 		unsigned long e = nodes[i].end >> PAGE_SHIFT;
 		pxmram += e - s;
 		pxmram -= absent_pages_in_range(s, e);
-		pxmram -= nodes_add[i].end - nodes_add[i].start;
 		if ((long)pxmram < 0)
 			pxmram = 0;
 	}
@@ -459,3 +466,16 @@ int __node_distance(int a, int b)
 }
 
 EXPORT_SYMBOL(__node_distance);
+
+int memory_add_physaddr_to_nid(u64 start)
+{
+	int i, ret = 0;
+
+	for_each_node(i)
+		if (nodes_add[i].start <= start && nodes_add[i].end > start)
+			ret = i;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+