7 files changed, 53 insertions, 66 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index dfbf70e65860..942ccf1256ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -48,6 +48,7 @@
 #include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
+#include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/reboot.h>
@@ -138,24 +139,23 @@ static void xen_vcpu_setup(int cpu)
  */
 void xen_vcpu_restore(void)
 {
-	if (have_vcpu_info_placement) {
-		int cpu;
+	int cpu;
 
-		for_each_online_cpu(cpu) {
-			bool other_cpu = (cpu != smp_processor_id());
+	for_each_online_cpu(cpu) {
+		bool other_cpu = (cpu != smp_processor_id());
 
-			if (other_cpu &&
-			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
-				BUG();
+		if (other_cpu &&
+		    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+			BUG();
 
-			xen_vcpu_setup(cpu);
+		xen_setup_runstate_info(cpu);
 
-			if (other_cpu &&
-			    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
-				BUG();
-		}
+		if (have_vcpu_info_placement)
+			xen_vcpu_setup(cpu);
 
-		BUG_ON(!have_vcpu_info_placement);
+		if (other_cpu &&
+		    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+			BUG();
 	}
 }
 
@@ -924,7 +924,7 @@ static const struct pv_init_ops xen_init_ops __initdata = {
 };
 
 static const struct pv_time_ops xen_time_ops __initdata = {
-	.sched_clock = xen_sched_clock,
+	.sched_clock = xen_clocksource_read,
 };
 
 static const struct pv_cpu_ops xen_cpu_ops __initdata = {
@@ -1093,6 +1093,12 @@ asmlinkage void __init xen_start_kernel(void)
 
 	__supported_pte_mask |= _PAGE_IOMAP;
 
+	/*
+	 * Prevent page tables from being allocated in highmem, even
+	 * if CONFIG_HIGHPTE is enabled.
+	 */
+	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+
 #ifdef CONFIG_X86_64
 	/* Work out if we support NX */
 	check_efer();
@@ -1182,6 +1188,8 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_raw_console_write("about to get started...\n");
 
+	xen_setup_runstate_info(0);
+
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3bf7b1d250ce..350a3deedf25 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -185,7 +185,7 @@ static inline unsigned p2m_index(unsigned long pfn)
 }
 
 /* Build the parallel p2m_top_mfn structures */
-static void __init xen_build_mfn_list_list(void)
+void xen_build_mfn_list_list(void)
 {
 	unsigned pfn, idx;
 
@@ -1432,14 +1432,15 @@ static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
 {
 	pgprot_t prot = PAGE_KERNEL;
 
+	/*
+	 * We disable highmem allocations for page tables so we should never
+	 * see any calls to kmap_atomic_pte on a highmem page.
+	 */
+	BUG_ON(PageHighMem(page));
+
 	if (PagePinned(page))
 		prot = PAGE_KERNEL_RO;
 
-	if (0 && PageHighMem(page))
-		printk("mapping highpte %lx type %d prot %s\n",
-		       page_to_pfn(page), type,
-		       (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ");
-
 	return kmap_atomic_prot(page, type, prot);
 }
 #endif
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index fe03eeed7b48..360f8d8c19cd 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -295,6 +295,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu)
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
 #endif
+	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_init_lock_cpu(cpu);
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 95be7b434724..a9c661108034 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <linux/clockchips.h>
 
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
@@ -27,6 +28,8 @@ void xen_pre_suspend(void)
 
 void xen_post_suspend(int suspend_cancelled)
 {
+	xen_build_mfn_list_list();
+
 	xen_setup_shared_info();
 
 	if (suspend_cancelled) {
@@ -44,7 +47,19 @@ void xen_post_suspend(int suspend_cancelled)
 
 }
 
+static void xen_vcpu_notify_restore(void *data)
+{
+	unsigned long reason = (unsigned long)data;
+
+	/* Boot processor notified via generic timekeeping_resume() */
+	if ( smp_processor_id() == 0)
+		return;
+
+	clockevents_notify(reason, NULL);
+}
+
 void xen_arch_resume(void)
 {
-	/* nothing */
+	on_each_cpu(xen_vcpu_notify_restore,
+		    (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
 }
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0a5aa44299a5..8e04980d4697 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -100,7 +100,7 @@ bool xen_vcpu_stolen(int vcpu)
 	return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
 }
 
-static void setup_runstate_info(int cpu)
+void xen_setup_runstate_info(int cpu)
 {
 	struct vcpu_register_runstate_memory_area area;
 
@@ -154,45 +154,6 @@ static void do_stolen_accounting(void)
 	account_idle_ticks(ticks);
 }
 
-/*
- * Xen sched_clock implementation.  Returns the number of unstolen
- * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED
- * states.
- */
-unsigned long long xen_sched_clock(void)
-{
-	struct vcpu_runstate_info state;
-	cycle_t now;
-	u64 ret;
-	s64 offset;
-
-	/*
-	 * Ideally sched_clock should be called on a per-cpu basis
-	 * anyway, so preempt should already be disabled, but that's
-	 * not current practice at the moment.
-	 */
-	preempt_disable();
-
-	now = xen_clocksource_read();
-
-	get_runstate_snapshot(&state);
-
-	WARN_ON(state.state != RUNSTATE_running);
-
-	offset = now - state.state_entry_time;
-	if (offset < 0)
-		offset = 0;
-
-	ret = state.time[RUNSTATE_blocked] +
-		state.time[RUNSTATE_running] +
-		offset;
-
-	preempt_enable();
-
-	return ret;
-}
-
-
 /* Get the TSC speed from Xen */
 unsigned long xen_tsc_khz(void)
 {
@@ -434,7 +395,7 @@ void xen_setup_timer(int cpu)
 		name = "<timer kasprintf failed>";
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
-				      IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				      IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER,
 				      name, NULL);
 
 	evt = &per_cpu(xen_clock_events, cpu);
@@ -442,8 +403,6 @@ void xen_setup_timer(int cpu)
 
 	evt->cpumask = cpumask_of(cpu);
 	evt->irq = irq;
-
-	setup_runstate_info(cpu);
 }
 
 void xen_teardown_timer(int cpu)
@@ -494,6 +453,7 @@ __init void xen_time_init(void)
 
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
+	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();
 }
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 02f496a8dbaa..53adefda4275 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -96,7 +96,7 @@ ENTRY(xen_sysret32)
 	pushq $__USER32_CS
 	pushq %rcx
 
-	pushq $VGCF_in_syscall
+	pushq $0
 1:	jmp hypercall_iret
 ENDPATCH(xen_sysret32)
 RELOC(xen_sysret32, 1b+1)
@@ -151,7 +151,7 @@ ENTRY(xen_syscall32_target)
 ENTRY(xen_sysenter_target)
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
-	pushq $VGCF_in_syscall
+	pushq $0
 	jmp hypercall_iret
 ENDPROC(xen_syscall32_target)
 ENDPROC(xen_sysenter_target)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 355fa6b99c9c..f9153a300bce 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -25,6 +25,7 @@ extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
 void xen_setup_shared_info(void);
+void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
@@ -41,6 +42,7 @@ void __init xen_build_dynamic_phys_to_machine(void);
 
 void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
+void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
 cycle_t xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);