21 files changed, 392 insertions, 130 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index a3ddad18aaa..fa2161d5003 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -150,6 +150,10 @@ static int __init acpi_sleep_setup(char *str)
 			acpi_realmode_flags |= 2;
 		if (strncmp(str, "s3_beep", 7) == 0)
 			acpi_realmode_flags |= 4;
+#ifdef CONFIG_HIBERNATION
+		if (strncmp(str, "s4_nohwsig", 10) == 0)
+			acpi_no_s4_hw_signature();
+#endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
 		str = strchr(str, ',');
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index c25210e6ac8..74697408576 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -667,7 +667,7 @@ static int get_device_resources(struct device *dev,
 	_bdf = calc_devid(pcidev->bus->number, pcidev->devfn);
 
 	/* device not translated by any IOMMU in the system? */
-	if (_bdf >= amd_iommu_last_bdf) {
+	if (_bdf > amd_iommu_last_bdf) {
 		*iommu = NULL;
 		*domain = NULL;
 		*bdf = 0xffff;
@@ -1085,7 +1085,7 @@ void prealloc_protection_domains(void)
 
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
 		devid = (dev->bus->number << 8) | dev->devfn;
-		if (devid >= amd_iommu_last_bdf)
+		if (devid > amd_iommu_last_bdf)
 			continue;
 		devid = amd_iommu_alias_table[devid];
 		if (domain_for_device(devid))
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index c9d8ff2eb13..d9a9da597e7 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -732,7 +732,7 @@ static int __init init_exclusion_range(struct ivmd_header *m)
 		set_device_exclusion_range(m->devid, m);
 		break;
 	case ACPI_IVMD_TYPE_ALL:
-		for (i = 0; i < amd_iommu_last_bdf; ++i)
+		for (i = 0; i <= amd_iommu_last_bdf; ++i)
 			set_device_exclusion_range(i, m);
 		break;
 	case ACPI_IVMD_TYPE_RANGE:
@@ -934,7 +934,7 @@ int __init amd_iommu_init(void)
 	/*
 	 * let all alias entries point to itself
 	 */
-	for (i = 0; i < amd_iommu_last_bdf; ++i)
+	for (i = 0; i <= amd_iommu_last_bdf; ++i)
 		amd_iommu_alias_table[i] = i;
 
 	/*
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index bf9b441331e..9ee24e6bc4b 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -219,7 +219,6 @@
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <linux/pm.h>
-#include <linux/pm_legacy.h>
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 0ea6a19bfdf..ad2b15a1334 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -468,7 +468,7 @@ void hpet_disable(void)
 #define RTC_NUM_INTS		1
 
 static unsigned long hpet_rtc_flags;
-static unsigned long hpet_prev_update_sec;
+static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
 static unsigned long hpet_t1_cmp;
@@ -575,6 +575,9 @@ int hpet_set_rtc_irq_bit(unsigned long bit_mask)
 
 	hpet_rtc_flags |= bit_mask;
 
+	if ((bit_mask & RTC_UIE) && !(oldbits & RTC_UIE))
+		hpet_prev_update_sec = -1;
+
 	if (!oldbits)
 		hpet_rtc_timer_init();
 
@@ -652,7 +655,7 @@ static void hpet_rtc_timer_reinit(void)
 		if (hpet_rtc_flags & RTC_PIE)
 			hpet_pie_count += lost_ints;
 		if (printk_ratelimit())
-			printk(KERN_WARNING "rtc: lost %d interrupts\n",
+			printk(KERN_WARNING "hpet1: lost %d rtc interrupts\n",
 				lost_ints);
 	}
 }
@@ -670,7 +673,8 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {
-		rtc_int_flag = RTC_UF;
+		if (hpet_prev_update_sec >= 0)
+			rtc_int_flag = RTC_UF;
 		hpet_prev_update_sec = curr_time.tm_sec;
 	}
 
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 0373e88de95..1f26fd9ec4f 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -43,10 +43,11 @@
 
 #define BUILD_IRQ(nr)				\
 	asmlinkage void IRQ_NAME(nr);		\
-	asm("\n.p2align\n"			\
+	asm("\n.text\n.p2align\n"		\
 	    "IRQ" #nr "_interrupt:\n\t"		\
 	    "push $~(" #nr ") ; "		\
-	    "jmp common_interrupt");
+	    "jmp common_interrupt\n"		\
+	    ".previous");
 
 #define BI(x,y) \
 	BUILD_IRQ(x##y)
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 43c019f85f0..6c27679ec6a 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -431,7 +431,6 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->ip = (unsigned long)p->ainsn.insn;
 }
 
-/* Called with kretprobe_lock held */
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
@@ -682,8 +681,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 
 	INIT_HLIST_HEAD(&empty_rp);
-	spin_lock_irqsave(&kretprobe_lock, flags);
-	head = kretprobe_inst_table_head(current);
+	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
@@ -732,7 +730,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	spin_unlock_irqrestore(&kretprobe_lock, flags);
+	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 8864230d55a..9fe478d9840 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -22,6 +22,7 @@
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
 #include <asm/system.h>
+#include <asm/cacheflush.h>
 
 #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
 static u32 kexec_pgd[1024] PAGE_ALIGNED;
@@ -85,10 +86,12 @@ static void load_segments(void)
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Currently nothing.
+ * Make control page executable.
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_x(image->control_code_page, 1);
 	return 0;
 }
 
@@ -98,27 +101,48 @@ int machine_kexec_prepare(struct kimage *image)
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_nx(image->control_code_page, 1);
 }
 
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
+	asmlinkage unsigned long
+		(*relocate_kernel_ptr)(unsigned long indirection_page,
+				       unsigned long control_page,
+				       unsigned long start_address,
+				       unsigned int has_pae,
+				       unsigned int preserve_context);
 
 	tracer_disable();
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
+	if (image->preserve_context) {
+#ifdef CONFIG_X86_IO_APIC
+		/* We need to put APICs in legacy mode so that we can
+		 * get timer interrupts in second kernel. kexec/kdump
+		 * paths already have calls to disable_IO_APIC() in
+		 * one form or other. kexec jump path also need
+		 * one.
+		 */
+		disable_IO_APIC();
+#endif
+	}
+
 	control_page = page_address(image->control_code_page);
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	memcpy(control_page, relocate_kernel, PAGE_SIZE/2);
 
+	relocate_kernel_ptr = control_page;
 	page_list[PA_CONTROL_PAGE] = __pa(control_page);
-	page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
 	page_list[PA_PGD] = __pa(kexec_pgd);
 	page_list[VA_PGD] = (unsigned long)kexec_pgd;
 #ifdef CONFIG_X86_PAE
@@ -131,6 +155,7 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
 	page_list[PA_PTE_1] = __pa(kexec_pte1);
 	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+	page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT);
 
 	/* The segment registers are funny things, they have both a
 	 * visible and an invisible part.  Whenever the visible part is
@@ -149,8 +174,10 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	set_idt(phys_to_virt(0),0);
 
 	/* now call it */
-	relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
-			image->start, cpu_has_pae);
+	image->start = relocate_kernel_ptr((unsigned long)image->head,
+					   (unsigned long)page_list,
+					   image->start, cpu_has_pae,
+					   image->preserve_context);
 }
 
 void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 9dd9262693a..c43caa3a91f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image)
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 0e867676b5a..6ba87830d4b 100644
--- a/arch/x86/kernel/module_64.c
+++ b/arch/x86/kernel/module_64.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/bug.h>
 
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 151f2d171f7..b67a4b1d4ea 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/crash_dump.h>
 #include <linux/dma-mapping.h>
 #include <linux/bitops.h>
 #include <linux/pci_ids.h>
@@ -36,6 +37,7 @@
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+
 #include <asm/iommu.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
@@ -167,6 +169,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl);
 static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
 static void calioc2_tce_cache_blast(struct iommu_table *tbl);
 static void calioc2_dump_error_regs(struct iommu_table *tbl);
+static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl);
+static void get_tce_space_from_tar(void);
 
 static struct cal_chipset_ops calgary_chip_ops = {
 	.handle_quirks = calgary_handle_quirks,
@@ -410,22 +414,6 @@ static void calgary_unmap_sg(struct device *dev,
 	}
 }
 
-static int calgary_nontranslate_map_sg(struct device* dev,
-	struct scatterlist *sg, int nelems, int direction)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i) {
-		struct page *p = sg_page(s);
-
-		BUG_ON(!p);
-		s->dma_address = virt_to_bus(sg_virt(s));
-		s->dma_length = s->length;
-	}
-	return nelems;
-}
-
 static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	int nelems, int direction)
 {
@@ -436,9 +424,6 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long entry;
 	int i;
 
-	if (!translation_enabled(tbl))
-		return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
-
 	for_each_sg(sg, s, nelems, i) {
 		BUG_ON(!sg_page(s));
 
@@ -474,7 +459,6 @@ error:
 static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	size_t size, int direction)
 {
-	dma_addr_t dma_handle = bad_dma_address;
 	void *vaddr = phys_to_virt(paddr);
 	unsigned long uaddr;
 	unsigned int npages;
@@ -483,12 +467,7 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	uaddr = (unsigned long)vaddr;
 	npages = num_dma_pages(uaddr, size);
 
-	if (translation_enabled(tbl))
-		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction);
-	else
-		dma_handle = virt_to_bus(vaddr);
-
-	return dma_handle;
+	return iommu_alloc(dev, tbl, vaddr, npages, direction);
 }
 
 static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
@@ -497,9 +476,6 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
 	struct iommu_table *tbl = find_iommu_table(dev);
 	unsigned int npages;
 
-	if (!translation_enabled(tbl))
-		return;
-
 	npages = num_dma_pages(dma_handle, size);
 	iommu_free(tbl, dma_handle, npages);
 }
@@ -522,18 +498,12 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 		goto error;
 	memset(ret, 0, size);
 
-	if (translation_enabled(tbl)) {
-		/* set up tces to cover the allocated range */
-		mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-		if (mapping == bad_dma_address)
-			goto free;
-
-		*dma_handle = mapping;
-	} else /* non translated slot */
-		*dma_handle = virt_to_bus(ret);
-
+	/* set up tces to cover the allocated range */
+	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
+	if (mapping == bad_dma_address)
+		goto free;
+	*dma_handle = mapping;
 	return ret;
-
 free:
 	free_pages((unsigned long)ret, get_order(size));
 	ret = NULL;
@@ -541,7 +511,7 @@ error:
 	return ret;
 }
 
-static const struct dma_mapping_ops calgary_dma_ops = {
+static struct dma_mapping_ops calgary_dma_ops = {
 	.alloc_coherent = calgary_alloc_coherent,
 	.map_single = calgary_map_single,
 	.unmap_single = calgary_unmap_single,
@@ -830,7 +800,11 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
 
 	tbl = pci_iommu(dev->bus);
 	tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space;
-	tce_free(tbl, 0, tbl->it_size);
+
+	if (is_kdump_kernel())
+		calgary_init_bitmap_from_tce_table(tbl);
+	else
+		tce_free(tbl, 0, tbl->it_size);
 
 	if (is_calgary(dev->device))
 		tbl->chip_ops = &calgary_chip_ops;
@@ -1209,6 +1183,10 @@ static int __init calgary_init(void)
 	if (ret)
 		return ret;
 
+	/* Purely for kdump kernel case */
+	if (is_kdump_kernel())
+		get_tce_space_from_tar();
+
 	do {
 		dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
 		if (!dev)
@@ -1230,6 +1208,16 @@ static int __init calgary_init(void)
 			goto error;
 	} while (1);
 
+	dev = NULL;
+	for_each_pci_dev(dev) {
+		struct iommu_table *tbl;
+
+		tbl = find_iommu_table(&dev->dev);
+
+		if (translation_enabled(tbl))
+			dev->dev.archdata.dma_ops = &calgary_dma_ops;
+	}
+
 	return ret;
 
 error:
@@ -1251,6 +1239,7 @@ error:
 		calgary_disable_translation(dev);
 		calgary_free_bus(dev);
 		pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */
+		dev->dev.archdata.dma_ops = NULL;
 	} while (1);
 
 	return ret;
@@ -1339,6 +1328,61 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
 	return (val != 0xffffffff);
 }
 
+/*
+ * calgary_init_bitmap_from_tce_table():
+ * Funtion for kdump case. In the second/kdump kernel initialize
+ * the bitmap based on the tce table entries obtained from first kernel
+ */
+static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
+{
+	u64 *tp;
+	unsigned int index;
+	tp = ((u64 *)tbl->it_base);
+	for (index = 0 ; index < tbl->it_size; index++) {
+		if (*tp != 0x0)
+			set_bit(index, tbl->it_map);
+		tp++;
+	}
+}
+
+/*
+ * get_tce_space_from_tar():
+ * Function for kdump case. Get the tce tables from first kernel
+ * by reading the contents of the base adress register of calgary iommu
+ */
+static void get_tce_space_from_tar()
+{
+	int bus;
+	void __iomem *target;
+	unsigned long tce_space;
+
+	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
+		struct calgary_bus_info *info = &bus_info[bus];
+		unsigned short pci_device;
+		u32 val;
+
+		val = read_pci_config(bus, 0, 0, 0);
+		pci_device = (val & 0xFFFF0000) >> 16;
+
+		if (!is_cal_pci_dev(pci_device))
+			continue;
+		if (info->translation_disabled)
+			continue;
+
+		if (calgary_bus_has_devices(bus, pci_device) ||
+						translate_empty_slots) {
+			target = calgary_reg(bus_info[bus].bbar,
+						tar_offset(bus));
+			tce_space = be64_to_cpu(readq(target));
+			tce_space = tce_space & TAR_SW_BITS;
+
+			tce_space = tce_space & (~specified_table_size);
+			info->tce_space = (u64 *)__va(tce_space);
+		}
+	}
+	return;
+}
+
 void __init detect_calgary(void)
 {
 	int bus;
@@ -1394,7 +1438,8 @@ void __init detect_calgary(void)
 		return;
 	}
 
-	specified_table_size = determine_tce_table_size(max_pfn * PAGE_SIZE);
+	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
+					saved_max_pfn : max_pfn) * PAGE_SIZE);
 
 	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
 		struct calgary_bus_info *info = &bus_info[bus];
@@ -1412,10 +1457,16 @@ void __init detect_calgary(void)
 
 		if (calgary_bus_has_devices(bus, pci_device) ||
 		    translate_empty_slots) {
-			tbl = alloc_tce_table();
-			if (!tbl)
-				goto cleanup;
-			info->tce_space = tbl;
+			/*
+			 * If it is kdump kernel, find and use tce tables
+			 * from first kernel, else allocate tce tables here
+			 */
+			if (!is_kdump_kernel()) {
+				tbl = alloc_tce_table();
+				if (!tbl)
+					goto cleanup;
+				info->tce_space = tbl;
+			}
 			calgary_found = 1;
 		}
 	}
@@ -1430,6 +1481,10 @@ void __init detect_calgary(void)
 		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
 		       "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
 		       debugging ? "enabled" : "disabled");
+
+		/* swiotlb for devices that aren't behind the Calgary. */
+		if (max_pfn > MAX_DMA32_PFN)
+			swiotlb = 1;
 	}
 	return;
 
@@ -1446,7 +1501,7 @@ int __init calgary_iommu_init(void)
 {
 	int ret;
 
-	if (no_iommu || swiotlb)
+	if (no_iommu || (swiotlb && !calgary_detected))
 		return -ENODEV;
 
 	if (!calgary_detected)
@@ -1459,15 +1514,14 @@ int __init calgary_iommu_init(void)
 	if (ret) {
 		printk(KERN_ERR "PCI-DMA: Calgary init failed %d, "
 		       "falling back to no_iommu\n", ret);
-		if (max_pfn > MAX_DMA32_PFN)
-			printk(KERN_ERR "WARNING more than 4GB of memory, "
-					"32bit PCI may malfunction.\n");
 		return ret;
 	}
 
 	force_iommu = 1;
 	bad_dma_address = 0x0;
-	dma_ops = &calgary_dma_ops;
+	/* dma_ops is set to swiotlb or nommu */
+	if (!dma_ops)
+		dma_ops = &nommu_dma_ops;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index cbecb05551b..37544123896 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,7 +11,7 @@
 
 static int forbid_dac __read_mostly;
 
-const struct dma_mapping_ops *dma_ops;
+struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr)
 
 int dma_supported(struct device *dev, u64 mask)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
 		dev_info(dev, "PCI: Disallowing DAC for device\n");
@@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask)
 	}
 #endif
 
-	if (dma_ops->dma_supported)
-		return dma_ops->dma_supported(dev, mask);
+	if (ops->dma_supported)
+		return ops->dma_supported(dev, mask);
 
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
@@ -367,6 +369,7 @@ void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		   gfp_t gfp)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
 	void *memory = NULL;
 	struct page *page;
 	unsigned long dma_mask = 0;
@@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 			/* Let low level make its own zone decisions */
 			gfp &= ~(GFP_DMA32|GFP_DMA);
 
-			if (dma_ops->alloc_coherent)
-				return dma_ops->alloc_coherent(dev, size,
+			if (ops->alloc_coherent)
+				return ops->alloc_coherent(dev, size,
 							   dma_handle, gfp);
 			return NULL;
 		}
@@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		}
 	}
 
-	if (dma_ops->alloc_coherent) {
+	if (ops->alloc_coherent) {
 		free_pages((unsigned long)memory, get_order(size));
 		gfp &= ~(GFP_DMA|GFP_DMA32);
-		return dma_ops->alloc_coherent(dev, size, dma_handle, gfp);
+		return ops->alloc_coherent(dev, size, dma_handle, gfp);
 	}
 
-	if (dma_ops->map_simple) {
-		*dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory),
+	if (ops->map_simple) {
+		*dma_handle = ops->map_simple(dev, virt_to_phys(memory),
 					      size,
 					      PCI_DMA_BIDIRECTIONAL);
 		if (*dma_handle != bad_dma_address)
@@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *dev, size_t size,
 			 void *vaddr, dma_addr_t bus)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
 	int order = get_order(size);
 	WARN_ON(irqs_disabled());	/* for portability */
 	if (dma_release_coherent(dev, order, vaddr))
 		return;
-	if (dma_ops->unmap_single)
-		dma_ops->unmap_single(dev, bus, size, 0);
+	if (ops->unmap_single)
+		ops->unmap_single(dev, bus, size, 0);
 	free_pages((unsigned long)vaddr, order);
 }
 EXPORT_SYMBOL(dma_free_coherent);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index df5f142657d..744126e6495 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -692,8 +692,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 extern int agp_amd64_init(void);
 
-static const struct dma_mapping_ops gart_dma_ops = {
-	.mapping_error			= NULL,
+static struct dma_mapping_ops gart_dma_ops = {
 	.map_single			= gart_map_single,
 	.map_simple			= gart_map_simple,
 	.unmap_single			= gart_unmap_single,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 792b9179eff..3f91f71cdc3 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 	return nents;
 }
 
-/* Make sure we keep the same behaviour */
-static int nommu_mapping_error(dma_addr_t dma_addr)
-{
-#ifdef CONFIG_X86_32
-	return 0;
-#else
-	return (dma_addr == bad_dma_address);
-#endif
-}
-
-
-const struct dma_mapping_ops nommu_dma_ops = {
+struct dma_mapping_ops nommu_dma_ops = {
 	.map_single = nommu_map_single,
 	.map_sg = nommu_map_sg,
-	.mapping_error = nommu_mapping_error,
 	.is_phys = 1,
 };
 
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 20df839b9c2..c4ce0332759 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 	return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
 }
 
-const struct dma_mapping_ops swiotlb_dma_ops = {
+struct dma_mapping_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc_coherent = swiotlb_alloc_coherent,
 	.free_coherent = swiotlb_free_coherent,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0c3927accb0..53bc653ed5c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,7 +128,7 @@ void cpu_idle(void)
 
 	/* endless idle loop with no priority at all */
 	while (1) {
-		tick_nohz_stop_sched_tick();
+		tick_nohz_stop_sched_tick(1);
 		while (!need_resched()) {
 
 			check_pgt_cache();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e8a8e1b9981..3fb62a7d9a1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -120,7 +120,7 @@ void cpu_idle(void)
 	current_thread_info()->status |= TS_POLLING;
 	/* endless idle loop with no priority at all */
 	while (1) {
-		tick_nohz_stop_sched_tick();
+		tick_nohz_stop_sched_tick(1);
 		while (!need_resched()) {
 
 			rmb();
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index c30fe25d470..703310a9902 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -20,11 +20,44 @@
 #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define PAE_PGD_ATTR (_PAGE_PRESENT)
 
+/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are
+ * used to save some data for jumping back
+ */
+#define DATA(offset)		(PAGE_SIZE/2+(offset))
+
+/* Minimal CPU state */
+#define ESP			DATA(0x0)
+#define CR0			DATA(0x4)
+#define CR3			DATA(0x8)
+#define CR4			DATA(0xc)
+
+/* other data */
+#define CP_VA_CONTROL_PAGE	DATA(0x10)
+#define CP_PA_PGD		DATA(0x14)
+#define CP_PA_SWAP_PAGE		DATA(0x18)
+#define CP_PA_BACKUP_PAGES_MAP	DATA(0x1c)
+
 	.text
 	.align PAGE_SIZE
 	.globl relocate_kernel
 relocate_kernel:
-	movl	8(%esp), %ebp /* list of pages */
+	/* Save the CPU context, used for jumping back */
+
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	pushl	%ebp
+	pushf
+
+	movl	20+8(%esp), %ebp /* list of pages */
+	movl	PTR(VA_CONTROL_PAGE)(%ebp), %edi
+	movl	%esp, ESP(%edi)
+	movl	%cr0, %eax
+	movl	%eax, CR0(%edi)
+	movl	%cr3, %eax
+	movl	%eax, CR3(%edi)
+	movl	%cr4, %eax
+	movl	%eax, CR4(%edi)
 
 #ifdef CONFIG_X86_PAE
 	/* map the control page at its virtual address */
@@ -138,15 +171,25 @@ relocate_kernel:
 
 relocate_new_kernel:
 	/* read the arguments and say goodbye to the stack */
-	movl  4(%esp), %ebx /* page_list */
-	movl  8(%esp), %ebp /* list of pages */
-	movl  12(%esp), %edx /* start address */
-	movl  16(%esp), %ecx /* cpu_has_pae */
+	movl  20+4(%esp), %ebx /* page_list */
+	movl  20+8(%esp), %ebp /* list of pages */
+	movl  20+12(%esp), %edx /* start address */
+	movl  20+16(%esp), %ecx /* cpu_has_pae */
+	movl  20+20(%esp), %esi /* preserve_context */
 
 	/* zero out flags, and disable interrupts */
 	pushl $0
 	popfl
 
+	/* save some information for jumping back */
+	movl	PTR(VA_CONTROL_PAGE)(%ebp), %edi
+	movl	%edi, CP_VA_CONTROL_PAGE(%edi)
+	movl	PTR(PA_PGD)(%ebp), %eax
+	movl	%eax, CP_PA_PGD(%edi)
+	movl	PTR(PA_SWAP_PAGE)(%ebp), %eax
+	movl	%eax, CP_PA_SWAP_PAGE(%edi)
+	movl	%ebx, CP_PA_BACKUP_PAGES_MAP(%edi)
+
 	/* get physical address of control page now */
 	/* this is impossible after page table switch */
 	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edi
@@ -197,8 +240,90 @@ identity_mapped:
 	xorl	%eax, %eax
 	movl	%eax, %cr3
 
+	movl	CP_PA_SWAP_PAGE(%edi), %eax
+	pushl	%eax
+	pushl	%ebx
+	call	swap_pages
+	addl	$8, %esp
+
+	/* To be certain of avoiding problems with self-modifying code
+	 * I need to execute a serializing instruction here.
+	 * So I flush the TLB, it's handy, and not processor dependent.
+	 */
+	xorl	%eax, %eax
+	movl	%eax, %cr3
+
+	/* set all of the registers to known values */
+	/* leave %esp alone */
+
+	testl	%esi, %esi
+	jnz 1f
+	xorl	%edi, %edi
+	xorl	%eax, %eax
+	xorl	%ebx, %ebx
+	xorl    %ecx, %ecx
+	xorl    %edx, %edx
+	xorl    %esi, %esi
+	xorl    %ebp, %ebp
+	ret
+1:
+	popl	%edx
+	movl	CP_PA_SWAP_PAGE(%edi), %esp
+	addl	$PAGE_SIZE, %esp
+2:
+	call	*%edx
+
+	/* get the re-entry point of the peer system */
+	movl	0(%esp), %ebp
+	call	1f
+1:
+	popl	%ebx
+	subl	$(1b - relocate_kernel), %ebx
+	movl	CP_VA_CONTROL_PAGE(%ebx), %edi
+	lea	PAGE_SIZE(%ebx), %esp
+	movl	CP_PA_SWAP_PAGE(%ebx), %eax
+	movl	CP_PA_BACKUP_PAGES_MAP(%ebx), %edx
+	pushl	%eax
+	pushl	%edx
+	call	swap_pages
+	addl	$8, %esp
+	movl	CP_PA_PGD(%ebx), %eax
+	movl	%eax, %cr3
+	movl	%cr0, %eax
+	orl	$(1<<31), %eax
+	movl	%eax, %cr0
+	lea	PAGE_SIZE(%edi), %esp
+	movl	%edi, %eax
+	addl	$(virtual_mapped - relocate_kernel), %eax
+	pushl	%eax
+	ret
+
+virtual_mapped:
+	movl	CR4(%edi), %eax
+	movl	%eax, %cr4
+	movl	CR3(%edi), %eax
+	movl	%eax, %cr3
+	movl	CR0(%edi), %eax
+	movl	%eax, %cr0
+	movl	ESP(%edi), %esp
+	movl	%ebp, %eax
+
+	popf
+	popl	%ebp
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	ret
+
 	/* Do the copies */
-	movl	%ebx, %ecx
+swap_pages:
+	movl	8(%esp), %edx
+	movl	4(%esp), %ecx
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%edi
+	pushl	%esi
+	movl	%ecx, %ebx
 	jmp	1f
 
 0:	/* top, read another word from the indirection page */
@@ -226,27 +351,28 @@ identity_mapped:
 	movl    %ecx,   %esi /* For every source page do a copy */
 	andl    $0xfffff000, %esi
 
+	movl	%edi, %eax
+	movl	%esi, %ebp
+
+	movl	%edx, %edi
 	movl    $1024, %ecx
 	rep ; movsl
-	jmp     0b
 
-3:
-
-	/* To be certain of avoiding problems with self-modifying code
-	 * I need to execute a serializing instruction here.
-	 * So I flush the TLB, it's handy, and not processor dependent.
-	 */
-	xorl	%eax, %eax
-	movl	%eax, %cr3
+	movl	%ebp, %edi
+	movl	%eax, %esi
+	movl	$1024, %ecx
+	rep ; movsl
 
-	/* set all of the registers to known values */
-	/* leave %esp alone */
+	movl	%eax, %edi
+	movl	%edx, %esi
+	movl	$1024, %ecx
+	rep ; movsl
 
-	xorl	%eax, %eax
-	xorl	%ebx, %ebx
-	xorl    %ecx, %ecx
-	xorl    %edx, %edx
-	xorl    %esi, %esi
-	xorl    %edi, %edi
-	xorl    %ebp, %ebp
+	lea	PAGE_SIZE(%ebp), %esi
+	jmp     0b
+3:
+	popl	%esi
+	popl	%edi
+	popl	%ebx
+	popl	%ebp
 	ret
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4aacb9f52e..b520dae02bf 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -597,11 +597,11 @@ void __init setup_arch(char **cmdline_p)
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
 	pre_setup_arch_hook();
-	early_cpu_init();
 #else
 	printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
+	early_cpu_init();
 	early_ioremap_init();
 
 	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
@@ -665,9 +665,6 @@ void __init setup_arch(char **cmdline_p)
 	bss_resource.start = virt_to_phys(&__bss_start);
 	bss_resource.end = virt_to_phys(&__bss_stop)-1;
 
-#ifdef CONFIG_X86_64
-	early_cpu_init();
-#endif
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 47c3d249e63..b45ef8ddd65 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 	return do_sigaltstack(uss, uoss, regs->sp);
 }
 
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err = 0;
+
+	BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
+			sizeof(tsk->thread.xstate->fxsave));
+
+	if ((unsigned long)buf % 16)
+		printk("save_i387: bad fpstate %p\n", buf);
+
+	if (!used_math())
+		return 0;
+	clear_used_math(); /* trigger finit */
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		err = save_i387_checking((struct i387_fxsave_struct __user *)
+					 buf);
+		if (err)
+			return err;
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		stts();
+	} else {
+		if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
+				   sizeof(struct i387_fxsave_struct)))
+			return -1;
+	}
+	return 1;
+}
+
+/*
+ * This restores directly out of user space. Exceptions are handled.
+ */
+static inline int restore_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err;
+
+	if (!used_math()) {
+		err = init_fpu(tsk);
+		if (err)
+			return err;
+	}
+
+	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
+		clts();
+		task_thread_info(current)->status |= TS_USEDFPU;
+	}
+	return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+}
 
 /*
  * Do a signal return; undo the signal stack.
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index adff5562f5f..d44395ff34c 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -326,3 +326,9 @@ ENTRY(sys_call_table)
 	.long sys_fallocate
 	.long sys_timerfd_settime	/* 325 */
 	.long sys_timerfd_gettime
+	.long sys_signalfd4
+	.long sys_eventfd2
+	.long sys_epoll_create1
+	.long sys_dup3			/* 330 */
+	.long sys_pipe2
+	.long sys_inotify_init1