8 files changed, 96 insertions, 127 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 138e5667409a..39928d16be3b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1517,72 +1517,51 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-#ifdef CONFIG_XEN_PVHVM
-#define HVM_SHARED_INFO_ADDR 0xFE700000UL
-static struct shared_info *xen_hvm_shared_info;
-static unsigned long xen_hvm_sip_phys;
-static int xen_major, xen_minor;
-
-static void xen_hvm_connect_shared_info(unsigned long pfn)
+void __ref xen_hvm_init_shared_info(void)
 {
+	int cpu;
 	struct xen_add_to_physmap xatp;
+	static struct shared_info *shared_info_page = 0;
 
+	if (!shared_info_page)
+		shared_info_page = (struct shared_info *)
+			extend_brk(PAGE_SIZE, PAGE_SIZE);
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = pfn;
+	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 
-}
-static void __init xen_hvm_set_shared_info(struct shared_info *sip)
-{
-	int cpu;
-
-	HYPERVISOR_shared_info = sip;
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
 
 	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
 	 * page, we use it in the event channel upcall and in some pvclock
 	 * related functions. We don't need the vcpu_info placement
 	 * optimizations because we don't use any pv_mmu or pv_irq op on
-	 * HVM. */
-	for_each_online_cpu(cpu)
+	 * HVM.
+	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+	 * online but xen_hvm_init_shared_info is run at resume time too and
+	 * in that case multiple vcpus might be online. */
+	for_each_online_cpu(cpu) {
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
-}
-
-/* Reconnect the shared_info pfn to a (new) mfn */
-void xen_hvm_resume_shared_info(void)
-{
-	xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
-}
-
-/* Xen tools prior to Xen 4 do not provide a E820_Reserved area for guest usage.
- * On these old tools the shared info page will be placed in E820_Ram.
- * Xen 4 provides a E820_Reserved area at 0xFC000000, and this code expects
- * that nothing is mapped up to HVM_SHARED_INFO_ADDR.
- * Xen 4.3+ provides an explicit 1MB area at HVM_SHARED_INFO_ADDR which is used
- * here for the shared info page. */
-static void __init xen_hvm_init_shared_info(void)
-{
-	if (xen_major < 4) {
-		xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		xen_hvm_sip_phys = __pa(xen_hvm_shared_info);
-	} else {
-		xen_hvm_sip_phys = HVM_SHARED_INFO_ADDR;
-		set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_hvm_sip_phys);
-		xen_hvm_shared_info =
-		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
 	}
-	xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
-	xen_hvm_set_shared_info(xen_hvm_shared_info);
 }
 
+#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
-	uint32_t ecx, edx, pages, msr, base;
+	int major, minor;
+	uint32_t eax, ebx, ecx, edx, pages, msr, base;
 	u64 pfn;
 
 	base = xen_cpuid_base();
+	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+
+	major = eax >> 16;
+	minor = eax & 0xffff;
+	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
+
 	cpuid(base + 2, &pages, &msr, &ecx, &edx);
 
 	pfn = __pa(hypercall_page);
@@ -1633,22 +1612,12 @@ static void __init xen_hvm_guest_init(void)
 
 static bool __init xen_hvm_platform(void)
 {
-	uint32_t eax, ebx, ecx, edx, base;
-
 	if (xen_pv_domain())
 		return false;
 
-	base = xen_cpuid_base();
-	if (!base)
+	if (!xen_cpuid_base())
 		return false;
 
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
-
-	xen_major = eax >> 16;
-	xen_minor = eax & 0xffff;
-
-	printk(KERN_INFO "Xen version %d.%d.\n", xen_major, xen_minor);
-
 	return true;
 }
 
@@ -1668,6 +1637,7 @@ const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
 	.name			= "Xen HVM",
 	.detect			= xen_hvm_platform,
 	.init_platform		= xen_hvm_guest_init,
+	.x2apic_available	= xen_x2apic_para_available,
 };
 EXPORT_SYMBOL(x86_hyper_xen_hvm);
 #endif
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 01de35c77221..e8e34938c57d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1178,20 +1178,6 @@ static void xen_exit_mmap(struct mm_struct *mm)
 
 static void xen_post_allocator_init(void);
 
-static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
-{
-	/* reserve the range used */
-	native_pagetable_reserve(start, end);
-
-	/* set as RW the rest */
-	printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
-			PFN_PHYS(pgt_buf_top));
-	while (end < PFN_PHYS(pgt_buf_top)) {
-		make_lowmem_page_readwrite(__va(end));
-		end += PAGE_SIZE;
-	}
-}
-
 #ifdef CONFIG_X86_64
 static void __init xen_cleanhighmap(unsigned long vaddr,
 				    unsigned long vaddr_end)
@@ -1422,7 +1408,6 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3)
 		xen_mc_callback(set_current_cr3, (void *)cr3);
 	}
 }
-
 static void xen_write_cr3(unsigned long cr3)
 {
 	BUG_ON(preemptible());
@@ -1448,6 +1433,45 @@ static void xen_write_cr3(unsigned long cr3)
 	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
 
+#ifdef CONFIG_X86_64
+/*
+ * At the start of the day - when Xen launches a guest, it has already
+ * built pagetables for the guest. We diligently look over them
+ * in xen_setup_kernel_pagetable and graft as appropiate them in the
+ * init_level4_pgt and its friends. Then when we are happy we load
+ * the new init_level4_pgt - and continue on.
+ *
+ * The generic code starts (start_kernel) and 'init_mem_mapping' sets
+ * up the rest of the pagetables. When it has completed it loads the cr3.
+ * N.B. that baremetal would start at 'start_kernel' (and the early
+ * #PF handler would create bootstrap pagetables) - so we are running
+ * with the same assumptions as what to do when write_cr3 is executed
+ * at this point.
+ *
+ * Since there are no user-page tables at all, we have two variants
+ * of xen_write_cr3 - the early bootup (this one), and the late one
+ * (xen_write_cr3). The reason we have to do that is that in 64-bit
+ * the Linux kernel and user-space are both in ring 3 while the
+ * hypervisor is in ring 0.
+ */
+static void __init xen_write_cr3_init(unsigned long cr3)
+{
+	BUG_ON(preemptible());
+
+	xen_mc_batch();  /* disables interrupts */
+
+	/* Update while interrupts are disabled, so its atomic with
+	   respect to ipis */
+	this_cpu_write(xen_cr3, cr3);
+
+	__xen_write_cr3(true, cr3);
+
+	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
+}
+#endif
+
 static int xen_pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd = mm->pgd;
@@ -1503,19 +1527,6 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 #else /* CONFIG_X86_64 */
 static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
-
-	/*
-	 * If the new pfn is within the range of the newly allocated
-	 * kernel pagetable, and it isn't being mapped into an
-	 * early_ioremap fixmap slot as a freshly allocated page, make sure
-	 * it is RO.
-	 */
-	if (((!is_early_ioremap_ptep(ptep) &&
-			pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
-			(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
-		pte = pte_wrprotect(pte);
-
 	return pte;
 }
 #endif /* CONFIG_X86_64 */
@@ -2129,11 +2140,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.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,
@@ -2197,7 +2204,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 
 void __init xen_init_mmu_ops(void)
 {
-	x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 	pv_mmu_ops = xen_mmu_ops;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8971a26d21ab..94eac5c85cdc 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -556,12 +556,9 @@ void __init xen_arch_setup(void)
 	       COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
 
 	/* Set up idle, making sure it calls safe_halt() pvop */
-#ifdef CONFIG_X86_32
-	boot_cpu_data.hlt_works_ok = 1;
-#endif
 	disable_cpuidle();
 	disable_cpufreq();
-	WARN_ON(set_pm_idle_to_default());
+	WARN_ON(xen_set_default_idle());
 	fiddle_vdso();
 #ifdef CONFIG_NUMA
 	numa_off = 1;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4f7d2599b484..09ea61d2e02f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -300,8 +300,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	gdt = get_cpu_gdt_table(cpu);
 
 	ctxt->flags = VGCF_IN_KERNEL;
-	ctxt->user_regs.ds = __USER_DS;
-	ctxt->user_regs.es = __USER_DS;
 	ctxt->user_regs.ss = __KERNEL_DS;
 #ifdef CONFIG_X86_32
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
@@ -310,35 +308,41 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
 	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
 
 	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
-	xen_copy_trap_info(ctxt->trap_ctxt);
+	{
+		ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
+		ctxt->user_regs.ds = __USER_DS;
+		ctxt->user_regs.es = __USER_DS;
 
-	ctxt->ldt_ents = 0;
+		xen_copy_trap_info(ctxt->trap_ctxt);
 
-	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
+		ctxt->ldt_ents = 0;
 
-	gdt_mfn = arbitrary_virt_to_mfn(gdt);
-	make_lowmem_page_readonly(gdt);
-	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
+		BUG_ON((unsigned long)gdt & ~PAGE_MASK);
 
-	ctxt->gdt_frames[0] = gdt_mfn;
-	ctxt->gdt_ents      = GDT_ENTRIES;
+		gdt_mfn = arbitrary_virt_to_mfn(gdt);
+		make_lowmem_page_readonly(gdt);
+		make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
 
-	ctxt->user_regs.cs = __KERNEL_CS;
-	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
+		ctxt->gdt_frames[0] = gdt_mfn;
+		ctxt->gdt_ents      = GDT_ENTRIES;
 
-	ctxt->kernel_ss = __KERNEL_DS;
-	ctxt->kernel_sp = idle->thread.sp0;
+		ctxt->kernel_ss = __KERNEL_DS;
+		ctxt->kernel_sp = idle->thread.sp0;
 
 #ifdef CONFIG_X86_32
-	ctxt->event_callback_cs     = __KERNEL_CS;
-	ctxt->failsafe_callback_cs  = __KERNEL_CS;
+		ctxt->event_callback_cs     = __KERNEL_CS;
+		ctxt->failsafe_callback_cs  = __KERNEL_CS;
 #endif
-	ctxt->event_callback_eip    = (unsigned long)xen_hypervisor_callback;
-	ctxt->failsafe_callback_eip = (unsigned long)xen_failsafe_callback;
+		ctxt->event_callback_eip    =
+					(unsigned long)xen_hypervisor_callback;
+		ctxt->failsafe_callback_eip =
+					(unsigned long)xen_failsafe_callback;
+	}
+	ctxt->user_regs.cs = __KERNEL_CS;
+	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
 
 	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
 	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
@@ -432,13 +436,6 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
-	/*
-	 * Balance out the preempt calls - as we are running in cpu_idle
-	 * loop which has been called at bootup from cpu_bringup_and_idle.
-	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
-	 * preempt_disable() So this preempt_enable will balance it out.
-	 */
-	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 83e866d714ce..f7a080ef0354 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -328,7 +328,6 @@ static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
 		if (per_cpu(lock_spinners, cpu) == xl) {
 			ADD_STATS(released_slow_kicked, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
-			break;
 		}
 	}
 }
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index ae8a00c39de4..45329c8c226e 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
-	xen_hvm_resume_shared_info();
+	xen_hvm_init_shared_info();
 	xen_callback_vector();
 	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index f9643fc50de5..33ca6e42a4ca 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -89,11 +89,11 @@ ENTRY(xen_iret)
 	 */
 #ifdef CONFIG_SMP
 	GET_THREAD_INFO(%eax)
-	movl TI_cpu(%eax), %eax
-	movl __per_cpu_offset(,%eax,4), %eax
-	mov xen_vcpu(%eax), %eax
+	movl %ss:TI_cpu(%eax), %eax
+	movl %ss:__per_cpu_offset(,%eax,4), %eax
+	mov %ss:xen_vcpu(%eax), %eax
 #else
-	movl xen_vcpu, %eax
+	movl %ss:xen_vcpu, %eax
 #endif
 
 	/* check IF state we're restoring */
@@ -106,11 +106,11 @@ ENTRY(xen_iret)
 	 * resuming the code, so we don't have to be worried about
 	 * being preempted to another CPU.
 	 */
-	setz XEN_vcpu_info_mask(%eax)
+	setz %ss:XEN_vcpu_info_mask(%eax)
 xen_iret_start_crit:
 
 	/* check for unmasked and pending */
-	cmpw $0x0001, XEN_vcpu_info_pending(%eax)
+	cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
 
 	/*
 	 * If there's something pending, mask events again so we can
@@ -118,7 +118,7 @@ xen_iret_start_crit:
 	 * touch XEN_vcpu_info_mask.
 	 */
 	jne 1f
-	movb $1, XEN_vcpu_info_mask(%eax)
+	movb $1, %ss:XEN_vcpu_info_mask(%eax)
 
 1:	popl %eax
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index d2e73d19d366..a95b41744ad0 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -40,7 +40,7 @@ void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_resume_shared_info(void);
+void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);