+#ifdef CONFIG_X86_64
+/*
+ * Like __va(), but returns address in the kernel mapping (which is
+ * all we have until the physical memory mapping has been set up.
+ */
+static void *__ka(phys_addr_t paddr)
+{
+ return (void *)(paddr + __START_KERNEL_map);
+}
+
+/* Convert a machine address to physical address */
+static unsigned long m2p(phys_addr_t maddr)
+{
+ phys_addr_t paddr;
+
+ maddr &= PTE_MASK;
+ paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;
+
+ return paddr;
+}
+
+/* Convert a machine address to kernel virtual */
+static void *m2v(phys_addr_t maddr)
+{
+ return __ka(m2p(maddr));
+}
+
+static void walk(pgd_t *pgd, unsigned long addr)
+{
+ unsigned l4idx = pgd_index(addr);
+ unsigned l3idx = pud_index(addr);
+ unsigned l2idx = pmd_index(addr);
+ unsigned l1idx = pte_index(addr);
+ pgd_t l4;
+ pud_t l3;
+ pmd_t l2;
+ pte_t l1;
+
+ xen_raw_printk("walk %p, %lx -> %d %d %d %d\n",
+ pgd, addr, l4idx, l3idx, l2idx, l1idx);
+
+ l4 = pgd[l4idx];
+ xen_raw_printk(" l4: %016lx\n", l4.pgd);
+ xen_raw_printk(" %016lx\n", pgd_val(l4));
+
+ l3 = ((pud_t *)(m2v(l4.pgd)))[l3idx];
+ xen_raw_printk(" l3: %016lx\n", l3.pud);
+ xen_raw_printk(" %016lx\n", pud_val(l3));
+
+ l2 = ((pmd_t *)(m2v(l3.pud)))[l2idx];
+ xen_raw_printk(" l2: %016lx\n", l2.pmd);
+ xen_raw_printk(" %016lx\n", pmd_val(l2));
+
+ l1 = ((pte_t *)(m2v(l2.pmd)))[l1idx];
+ xen_raw_printk(" l1: %016lx\n", l1.pte);
+ xen_raw_printk(" %016lx\n", pte_val(l1));
+}
+
+static void set_page_prot(void *addr, pgprot_t prot)
+{
+ unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+ pte_t pte = pfn_pte(pfn, prot);
+
+ xen_raw_printk("addr=%p pfn=%lx mfn=%lx prot=%016x pte=%016x\n",
+ addr, pfn, get_phys_to_machine(pfn),
+ pgprot_val(prot), pte.pte);
+
+ if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+ BUG();
+}
+
+static void convert_pfn_mfn(void *v)
+{
+ pte_t *pte = v;
+ int i;
+
+ /* All levels are converted the same way, so just treat them
+ as ptes. */
+ for(i = 0; i < PTRS_PER_PTE; i++)
+ pte[i] = xen_make_pte(pte[i].pte);
+}
+
+/*
+ * Identity map, in addition to plain kernel map. This needs to be
+ * large enough to allocate page table pages to allocate the rest.
+ * Each page can map 2MB.
+ */
+static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;
+
+static __init void xen_map_identity_early(unsigned long max_pfn)
+{
+ unsigned pmdidx, pteidx;
+ unsigned ident_pte;
+ unsigned long pfn;
+
+ ident_pte = 0;
+ pfn = 0;
+ for(pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+ pte_t *pte_page;
+
+ BUG_ON(level2_ident_pgt[pmdidx].pmd != level2_kernel_pgt[pmdidx].pmd);
+
+ /* Reuse or allocate a page of ptes */
+ if (pmd_present(level2_ident_pgt[pmdidx]))
+ pte_page = m2v(level2_ident_pgt[pmdidx].pmd);
+ else {
+ /* Check for free pte pages */
+ if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
+ break;
+
+ pte_page = &level1_ident_pgt[ident_pte];
+ ident_pte += PTRS_PER_PTE;
+
+ /* Install new l1 in l2(s) */
+ level2_ident_pgt[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
+ level2_kernel_pgt[pmdidx] = level2_ident_pgt[pmdidx];
+ }
+
+ /* Install mappings */
+ for(pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+ pte_t pte;
+
+ if (pfn > max_pfn_mapped)
+ max_pfn_mapped = pfn;
+
+ if (!pte_none(pte_page[pteidx]))
+ continue;
+
+ pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
+ pte_page[pteidx] = pte;
+ }
+ }
+
+ for(pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+ set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
+}
+
+/*
+ * Set up the inital kernel pagetable.
+ *
+ * We can construct this by grafting the Xen provided pagetable into
+ * head_64.S's preconstructed pagetables. We copy the Xen L2's into
+ * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This
+ * means that only the kernel has a physical mapping to start with -
+ * but that's enough to get __va working. We need to fill in the rest
+ * of the physical mapping once some sort of allocator has been set
+ * up.
+ */
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+ pud_t *l3;
+ pmd_t *l2;
+
+ /* Zap identity mapping */
+ init_level4_pgt[0] = __pgd(0);
+
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ convert_pfn_mfn(init_level4_pgt);
+ convert_pfn_mfn(level3_ident_pgt);
+ convert_pfn_mfn(level3_kernel_pgt);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
+
+ memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+ memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
+ l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
+ memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
+
+ /* Set up identity map */
+ xen_map_identity_early(max_pfn);
+
+ /* Make pagetable pieces RO */
+ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+
+ /* Switch over */
+ pgd = init_level4_pgt;
+ xen_write_cr3(__pa(pgd));
+
+ reserve_early(__pa(xen_start_info->pt_base),
+ __pa(xen_start_info->pt_base +
+ xen_start_info->nr_pt_frames * PAGE_SIZE),
+ "XEN PAGETABLES");
+
+ return pgd;
+}
+#else
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+{
+ init_pg_tables_start = __pa(pgd);
+ init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
+ max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024);
+
+ x86_write_percpu(xen_cr3, __pa(pgd));
+ x86_write_percpu(xen_current_cr3, __pa(pgd));
+
+ return pgd;
+}
+#endif /* CONFIG_X86_64 */
+