11 files changed, 239 insertions, 111 deletions

diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index c25210e6ac88..74697408576f 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 c9d8ff2eb130..d9a9da597e79 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/head_32.S b/arch/x86/kernel/head_32.S
index f67e93441caf..a7010c3a377a 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -456,9 +456,6 @@ is386:	movl $2,%ecx		# set MP
 1:
 #endif /* CONFIG_SMP */
         jmp *(initial_code)
-.align 4
-ENTRY(initial_code)
-        .long i386_start_kernel
 
 /*
  * We depend on ET to be correct. This checks for 287/387.
@@ -601,6 +598,11 @@ ignore_int:
 #endif
         iret
 
+.section .cpuinit.data,"wa"
+.align 4
+ENTRY(initial_code)
+        .long i386_start_kernel
+
 .section .text
 /*
  * Real beginning of normal "text" segment
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 8864230d55af..9fe478d98406 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 9dd9262693a3..c43caa3a91f3 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/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 19e7fc7c2c4f..b67a4b1d4eae 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -37,6 +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>
@@ -413,22 +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)
 {
@@ -439,9 +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));
 
@@ -477,7 +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;
@@ -486,12 +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,
@@ -500,9 +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);
 }
@@ -525,18 +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;
@@ -544,7 +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,
@@ -1241,6 +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:
@@ -1262,6 +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;
@@ -1503,6 +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;
 
@@ -1519,7 +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)
@@ -1532,15 +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 cbecb05551bb..37544123896d 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 df5f142657d2..744126e64950 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 792b9179eff3..3f91f71cdc3e 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 20df839b9c20..c4ce0332759e 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/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index c30fe25d470d..703310a99023 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