6 files changed, 119 insertions, 70 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 235c0f4d3861..44dcad43989d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,6 +75,11 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
 EXPORT_SYMBOL_GPL(xen_domain_type);
 
+unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
+EXPORT_SYMBOL(machine_to_phys_mapping);
+unsigned int   machine_to_phys_order;
+EXPORT_SYMBOL(machine_to_phys_order);
+
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
 
@@ -1016,10 +1021,6 @@ static void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
 
-#ifdef CONFIG_SMP
-	stop_other_cpus();
-#endif
-
 	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
 		BUG();
 }
@@ -1090,6 +1091,8 @@ static void __init xen_setup_stackprotector(void)
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
+	struct physdev_set_iopl set_iopl;
+	int rc;
 	pgd_t *pgd;
 
 	if (!xen_start_info)
@@ -1097,6 +1100,8 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_domain_type = XEN_PV_DOMAIN;
 
+	xen_setup_machphys_mapping();
+
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
@@ -1191,8 +1196,6 @@ asmlinkage void __init xen_start_kernel(void)
 	/* Allocate and initialize top and mid mfn levels for p2m structure */
 	xen_build_mfn_list_list();
 
-	init_mm.pgd = pgd;
-
 	/* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32
@@ -1202,10 +1205,18 @@ asmlinkage void __init xen_start_kernel(void)
 #else
 	pv_info.kernel_rpl = 0;
 #endif
-
 	/* set the limit of our address space */
 	xen_reserve_top();
 
+	/* We used to do this in xen_arch_setup, but that is too late on AMD
+	 * were early_cpu_init (run before ->arch_setup()) calls early_amd_init
+	 * which pokes 0xcf8 port.
+	 */
+	set_iopl.iopl = 1;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+	if (rc != 0)
+		xen_raw_printk("physdev_op failed %d\n", rc);
+
 #ifdef CONFIG_X86_32
 	/* set up basic CPUID stuff */
 	cpu_detect(&new_cpu_data);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index c237b810b03f..44924e551fde 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2034,6 +2034,20 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 	set_page_prot(pmd, PAGE_KERNEL_RO);
 }
 
+void __init xen_setup_machphys_mapping(void)
+{
+	struct xen_machphys_mapping mapping;
+	unsigned long machine_to_phys_nr_ents;
+
+	if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
+		machine_to_phys_mapping = (unsigned long *)mapping.v_start;
+		machine_to_phys_nr_ents = mapping.max_mfn + 1;
+	} else {
+		machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+	}
+	machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+}
+
 #ifdef CONFIG_X86_64
 static void convert_pfn_mfn(void *v)
 {
@@ -2119,44 +2133,83 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	return pgd;
 }
 #else	/* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
+
+static __init void xen_write_cr3_init(unsigned long cr3)
+{
+	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
+
+	BUG_ON(read_cr3() != __pa(initial_page_table));
+	BUG_ON(cr3 != __pa(swapper_pg_dir));
+
+	/*
+	 * We are switching to swapper_pg_dir for the first time (from
+	 * initial_page_table) and therefore need to mark that page
+	 * read-only and then pin it.
+	 *
+	 * Xen disallows sharing of kernel PMDs for PAE
+	 * guests. Therefore we must copy the kernel PMD from
+	 * initial_page_table into a new kernel PMD to be used in
+	 * swapper_pg_dir.
+	 */
+	swapper_kernel_pmd =
+		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
+	memcpy(swapper_kernel_pmd, initial_kernel_pmd,
+	       sizeof(pmd_t) * PTRS_PER_PMD);
+	swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
+	set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
+
+	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+	xen_write_cr3(cr3);
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
+
+	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	set_page_prot(initial_page_table, PAGE_KERNEL);
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
+
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
+}
 
 __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
-	level2_kernel_pgt = extend_brk(sizeof(pmd_t *) * PTRS_PER_PMD, PAGE_SIZE);
+	initial_kernel_pmd =
+		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
 	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
 				  xen_start_info->nr_pt_frames * PAGE_SIZE +
 				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-	memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
 
-	xen_map_identity_early(level2_kernel_pgt, max_pfn);
+	xen_map_identity_early(initial_kernel_pmd, max_pfn);
 
-	memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
-	set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
-			__pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+	memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+	initial_page_table[KERNEL_PGD_BOUNDARY] =
+		__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
 
-	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
-	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+	set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
+	set_page_prot(initial_page_table, PAGE_KERNEL_RO);
 	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
 
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-	xen_write_cr3(__pa(swapper_pg_dir));
-
-	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+			  PFN_DOWN(__pa(initial_page_table)));
+	xen_write_cr3(__pa(initial_page_table));
 
 	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
 
-	return swapper_pg_dir;
+	return initial_page_table;
 }
 #endif	/* CONFIG_X86_64 */
 
@@ -2290,7 +2343,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.write_cr2 = xen_write_cr2,
 
 	.read_cr3 = xen_read_cr3,
+#ifdef CONFIG_X86_32
+	.write_cr3 = xen_write_cr3_init,
+#else
 	.write_cr3 = xen_write_cr3,
+#endif
 
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
@@ -2358,8 +2415,6 @@ void __init xen_init_mmu_ops(void)
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;
 
-	vmap_lazy_unmap = false;
-
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
 
@@ -2627,7 +2682,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 
 	prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
 
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
+				(VM_PFNMAP | VM_RESERVED | VM_IO)));
 
 	rmd.mfn = mfn;
 	rmd.prot = prot;
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 0f456386cce5..25c52f94a27c 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -68,7 +68,7 @@ static int __init check_platform_magic(void)
 	return 0;
 }
 
-void __init xen_unplug_emulated_devices(void)
+void xen_unplug_emulated_devices(void)
 {
 	int r;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b1dbdaa23ecc..b5a7f928234b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -23,7 +23,6 @@
 #include <xen/interface/callback.h>
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
-#include <xen/interface/memory.h>
 #include <xen/features.h>
 
 #include "xen-ops.h"
@@ -118,16 +117,18 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
 						     const struct e820map *e820)
 {
 	phys_addr_t max_addr = PFN_PHYS(max_pfn);
-	phys_addr_t last_end = 0;
+	phys_addr_t last_end = ISA_END_ADDRESS;
 	unsigned long released = 0;
 	int i;
 
+	/* Free any unused memory above the low 1Mbyte. */
 	for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
 		phys_addr_t end = e820->map[i].addr;
 		end = min(max_addr, end);
 
-		released += xen_release_chunk(last_end, end);
-		last_end = e820->map[i].addr + e820->map[i].size;
+		if (last_end < end)
+			released += xen_release_chunk(last_end, end);
+		last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
 	}
 
 	if (last_end < max_addr)
@@ -164,6 +165,7 @@ char * __init xen_memory_setup(void)
 		XENMEM_memory_map;
 	rc = HYPERVISOR_memory_op(op, &memmap);
 	if (rc == -ENOSYS) {
+		BUG_ON(xen_initial_domain());
 		memmap.nr_entries = 1;
 		map[0].addr = 0ULL;
 		map[0].size = mem_end;
@@ -179,34 +181,32 @@ char * __init xen_memory_setup(void)
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end = map[i].addr + map[i].size;
 
-		if (map[i].type == E820_RAM) {
-			if (map[i].addr < mem_end && end > mem_end) {
-				/* Truncate region to max_mem. */
-				u64 delta = end - mem_end;
+		if (map[i].type == E820_RAM && end > mem_end) {
+			/* RAM off the end - may be partially included */
+			u64 delta = min(map[i].size, end - mem_end);
 
-				map[i].size -= delta;
-				extra_pages += PFN_DOWN(delta);
+			map[i].size -= delta;
+			end -= delta;
 
-				end = mem_end;
-			}
+			extra_pages += PFN_DOWN(delta);
 		}
 
-		if (end > xen_extra_mem_start)
+		if (map[i].size > 0 && end > xen_extra_mem_start)
 			xen_extra_mem_start = end;
 
-		/* If region is non-RAM or below mem_end, add what remains */
-		if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
-		    map[i].size > 0)
+		/* Add region if any remains */
+		if (map[i].size > 0)
 			e820_add_region(map[i].addr, map[i].size, map[i].type);
 	}
 
 	/*
-	 * Even though this is normal, usable memory under Xen, reserve
-	 * ISA memory anyway because too many things think they can poke
+	 * In domU, the ISA region is normal, usable memory, but we
+	 * reserve ISA memory anyway because too many things poke
 	 * about in there.
 	 *
-	 * In a dom0 kernel, this region is identity mapped with the
-	 * hardware ISA area, so it really is out of bounds.
+	 * In Dom0, the host E820 information can leave gaps in the
+	 * ISA range, which would cause us to release those pages.  To
+	 * avoid this, we unconditionally reserve them here.
 	 */
 	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
 			E820_RESERVED);
@@ -244,26 +244,11 @@ char * __init xen_memory_setup(void)
 	else
 		extra_pages = 0;
 
-	if (!xen_initial_domain())
-		xen_add_extra_mem(extra_pages);
+	xen_add_extra_mem(extra_pages);
 
 	return "Xen";
 }
 
-static void xen_idle(void)
-{
-	local_irq_disable();
-
-	if (need_resched())
-		local_irq_enable();
-	else {
-		current_thread_info()->status &= ~TS_POLLING;
-		smp_mb__after_clear_bit();
-		safe_halt();
-		current_thread_info()->status |= TS_POLLING;
-	}
-}
-
 /*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
@@ -333,9 +318,6 @@ void __cpuinit xen_enable_syscall(void)
 
 void __init xen_arch_setup(void)
 {
-	struct physdev_set_iopl set_iopl;
-	int rc;
-
 	xen_panic_handler_init();
 
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -352,11 +334,6 @@ void __init xen_arch_setup(void)
 	xen_enable_sysenter();
 	xen_enable_syscall();
 
-	set_iopl.iopl = 1;
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-	if (rc != 0)
-		printk(KERN_INFO "physdev_op failed %d\n", rc);
-
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
 		printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
@@ -368,7 +345,11 @@ void __init xen_arch_setup(void)
 	       MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ?
 	       COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
 
-	pm_idle = xen_idle;
+	/* Set up idle, making sure it calls safe_halt() pvop */
+#ifdef CONFIG_X86_32
+	boot_cpu_data.hlt_works_ok = 1;
+#endif
+	pm_idle = default_idle;
 
 	fiddle_vdso();
 }
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 1d789d56877c..9bbd63a129b5 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -31,6 +31,7 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 	int cpu;
 	xen_hvm_init_shared_info();
 	xen_callback_vector();
+	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		for_each_online_cpu(cpu) {
 			xen_setup_runstate_info(cpu);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 64044747348e..9d41bf985757 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -43,7 +43,7 @@ void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
 void xen_hvm_init_shared_info(void);
-void __init xen_unplug_emulated_devices(void);
+void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);