Merge branch 'bugfix' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen

* 'bugfix' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen:
  xen: try harder to balloon up under memory pressure.
  Xen balloon: fix totalram_pages counting.
  xen: explicitly create/destroy stop_machine workqueues outside suspend/resume region.
  xen: improve error handling in do_suspend.
  xen: don't leak IRQs over suspend/resume.
  xen: call clock resume notifier on all CPUs
  xen: use iret for return from 64b kernel to 32b usermode
  xen: don't call dpm_resume_noirq() with interrupts disabled.
  xen: register runstate info for boot CPU early
  xen: register runstate on secondary CPUs
  xen: register timer interrupt with IRQF_TIMER
  xen: correctly restore pfn_to_mfn_list_list after resume
  xen: restore runstate_info even if !have_vcpu_info_placement
  xen: re-register runstate area earlier on resume.
  xen: wait up to 5 minutes for device connetion
  xen: improvement to wait_for_devices()
  xen: fix is_disconnected_device/exists_disconnected_device
  xen/xenbus: make DEVICE_ATTR()s static

11 files changed, 107 insertions, 79 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c462cea8ef09..b8e45f164e2a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -138,24 +138,23 @@ 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();
 	}
 }
 
@@ -1180,6 +1179,8 @@ 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..bf4cd6bfe959 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;
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 738da0cb0d8b..64757c0ba5fc 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..987267f79bf5 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 */
+	smp_call_function(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..9d1f853120d8 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;
 
@@ -434,7 +434,7 @@ 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 +442,6 @@ 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 +492,7 @@ __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);
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index d31505b6f7a4..420433613584 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -66,8 +66,6 @@ struct balloon_stats {
 	/* We aim for 'current allocation' == 'target allocation'. */
 	unsigned long current_pages;
 	unsigned long target_pages;
-	/* We may hit the hard limit in Xen. If we do then we remember it. */
-	unsigned long hard_limit;
 	/*
 	 * Drivers may alter the memory reservation independently, but they
 	 * must inform the balloon driver so we avoid hitting the hard limit.
@@ -136,6 +134,8 @@ static void balloon_append(struct page *page)
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
 	}
+
+	totalram_pages--;
 }
 
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
@@ -156,6 +156,8 @@ static struct page *balloon_retrieve(void)
 	else
 		balloon_stats.balloon_low--;
 
+	totalram_pages++;
+
 	return page;
 }
 
@@ -181,7 +183,7 @@ static void balloon_alarm(unsigned long unused)
 
 static unsigned long current_target(void)
 {
-	unsigned long target = min(balloon_stats.target_pages, balloon_stats.hard_limit);
+	unsigned long target = balloon_stats.target_pages;
 
 	target = min(target,
 		     balloon_stats.current_pages +
@@ -217,23 +219,10 @@ static int increase_reservation(unsigned long nr_pages)
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents = nr_pages;
 	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
-	if (rc < nr_pages) {
-		if (rc > 0) {
-			int ret;
-
-			/* We hit the Xen hard limit: reprobe. */
-			reservation.nr_extents = rc;
-			ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
-						   &reservation);
-			BUG_ON(ret != rc);
-		}
-		if (rc >= 0)
-			balloon_stats.hard_limit = (balloon_stats.current_pages + rc -
-						    balloon_stats.driver_pages);
+	if (rc < 0)
 		goto out;
-	}
 
-	for (i = 0; i < nr_pages; i++) {
+	for (i = 0; i < rc; i++) {
 		page = balloon_retrieve();
 		BUG_ON(page == NULL);
 
@@ -259,13 +248,12 @@ static int increase_reservation(unsigned long nr_pages)
 		__free_page(page);
 	}
 
-	balloon_stats.current_pages += nr_pages;
-	totalram_pages = balloon_stats.current_pages;
+	balloon_stats.current_pages += rc;
 
  out:
 	spin_unlock_irqrestore(&balloon_lock, flags);
 
-	return 0;
+	return rc < 0 ? rc : rc != nr_pages;
 }
 
 static int decrease_reservation(unsigned long nr_pages)
@@ -323,7 +311,6 @@ static int decrease_reservation(unsigned long nr_pages)
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;
-	totalram_pages = balloon_stats.current_pages;
 
 	spin_unlock_irqrestore(&balloon_lock, flags);
 
@@ -367,7 +354,6 @@ static void balloon_process(struct work_struct *work)
 static void balloon_set_new_target(unsigned long target)
 {
 	/* No need for lock. Not read-modify-write updates. */
-	balloon_stats.hard_limit   = ~0UL;
 	balloon_stats.target_pages = target;
 	schedule_work(&balloon_worker);
 }
@@ -422,12 +408,10 @@ static int __init balloon_init(void)
 	pr_info("xen_balloon: Initialising balloon driver.\n");
 
 	balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
-	totalram_pages   = balloon_stats.current_pages;
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
 	balloon_stats.driver_pages  = 0UL;
-	balloon_stats.hard_limit    = ~0UL;
 
 	init_timer(&balloon_timer);
 	balloon_timer.data = 0;
@@ -472,9 +456,6 @@ module_exit(balloon_exit);
 BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages));
 BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low));
 BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high));
-BALLOON_SHOW(hard_limit_kb,
-	     (balloon_stats.hard_limit!=~0UL) ? "%lu\n" : "???\n",
-	     (balloon_stats.hard_limit!=~0UL) ? PAGES2KB(balloon_stats.hard_limit) : 0);
 BALLOON_SHOW(driver_kb, "%lu\n", PAGES2KB(balloon_stats.driver_pages));
 
 static ssize_t show_target_kb(struct sys_device *dev, struct sysdev_attribute *attr,
@@ -544,7 +525,6 @@ static struct attribute *balloon_info_attrs[] = {
 	&attr_current_kb.attr,
 	&attr_low_kb.attr,
 	&attr_high_kb.attr,
-	&attr_hard_limit_kb.attr,
 	&attr_driver_kb.attr,
 	NULL
 };
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 2f57276e87a2..ce602dd09bc1 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -474,6 +474,9 @@ static void unbind_from_irq(unsigned int irq)
 		bind_evtchn_to_cpu(evtchn, 0);
 
 		evtchn_to_irq[evtchn] = -1;
+	}
+
+	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
 		dynamic_irq_cleanup(irq);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 10d03d7931c4..c4997930afc7 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -43,7 +43,6 @@ static int xen_suspend(void *data)
 	if (err) {
 		printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n",
 			err);
-		dpm_resume_noirq(PMSG_RESUME);
 		return err;
 	}
 
@@ -69,7 +68,6 @@ static int xen_suspend(void *data)
 	}
 
 	sysdev_resume();
-	dpm_resume_noirq(PMSG_RESUME);
 
 	return 0;
 }
@@ -81,6 +79,12 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
+	err = stop_machine_create();
+	if (err) {
+		printk(KERN_ERR "xen suspend: failed to setup stop_machine %d\n", err);
+		goto out;
+	}
+
 #ifdef CONFIG_PREEMPT
 	/* If the kernel is preemptible, we need to freeze all the processes
 	   to prevent them from being in the middle of a pagetable update
@@ -88,29 +92,32 @@ static void do_suspend(void)
 	err = freeze_processes();
 	if (err) {
 		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
-		return;
+		goto out_destroy_sm;
 	}
 #endif
 
 	err = dpm_suspend_start(PMSG_SUSPEND);
 	if (err) {
 		printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", err);
-		goto out;
+		goto out_thaw;
 	}
 
-	printk(KERN_DEBUG "suspending xenstore...\n");
-	xs_suspend();
-
 	err = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (err) {
 		printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err);
-		goto resume_devices;
+		goto out_resume;
 	}
 
+	printk(KERN_DEBUG "suspending xenstore...\n");
+	xs_suspend();
+
 	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
+
+	dpm_resume_noirq(PMSG_RESUME);
+
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
-		goto out;
+		cancelled = 1;
 	}
 
 	if (!cancelled) {
@@ -119,17 +126,21 @@ static void do_suspend(void)
 	} else
 		xs_suspend_cancel();
 
-	dpm_resume_noirq(PMSG_RESUME);
-
-resume_devices:
+out_resume:
 	dpm_resume_end(PMSG_RESUME);
 
 	/* Make sure timer events get retriggered on all CPUs */
 	clock_was_set();
-out:
+
+out_thaw:
 #ifdef CONFIG_PREEMPT
 	thaw_processes();
+
+out_destroy_sm:
 #endif
+	stop_machine_destroy();
+
+out:
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_PM_SLEEP */
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index d42e25d5968d..649fcdf114b7 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -454,21 +454,21 @@ static ssize_t xendev_show_nodename(struct device *dev,
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->nodename);
 }
-DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL);
+static DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL);
 
 static ssize_t xendev_show_devtype(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->devicetype);
 }
-DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL);
+static DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL);
 
 static ssize_t xendev_show_modalias(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "xen:%s\n", to_xenbus_device(dev)->devicetype);
 }
-DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL);
+static DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL);
 
 int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
@@ -843,7 +843,7 @@ postcore_initcall(xenbus_probe_init);
 
 MODULE_LICENSE("GPL");
 
-static int is_disconnected_device(struct device *dev, void *data)
+static int is_device_connecting(struct device *dev, void *data)
 {
 	struct xenbus_device *xendev = to_xenbus_device(dev);
 	struct device_driver *drv = data;
@@ -861,14 +861,15 @@ static int is_disconnected_device(struct device *dev, void *data)
 		return 0;
 
 	xendrv = to_xenbus_driver(dev->driver);
-	return (xendev->state != XenbusStateConnected ||
-		(xendrv->is_ready && !xendrv->is_ready(xendev)));
+	return (xendev->state < XenbusStateConnected ||
+		(xendev->state == XenbusStateConnected &&
+		 xendrv->is_ready && !xendrv->is_ready(xendev)));
 }
 
-static int exists_disconnected_device(struct device_driver *drv)
+static int exists_connecting_device(struct device_driver *drv)
 {
 	return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
-				is_disconnected_device);
+				is_device_connecting);
 }
 
 static int print_device_status(struct device *dev, void *data)
@@ -884,10 +885,13 @@ static int print_device_status(struct device *dev, void *data)
 		/* Information only: is this too noisy? */
 		printk(KERN_INFO "XENBUS: Device with no driver: %s\n",
 		       xendev->nodename);
-	} else if (xendev->state != XenbusStateConnected) {
+	} else if (xendev->state < XenbusStateConnected) {
+		enum xenbus_state rstate = XenbusStateUnknown;
+		if (xendev->otherend)
+			rstate = xenbus_read_driver_state(xendev->otherend);
 		printk(KERN_WARNING "XENBUS: Timeout connecting "
-		       "to device: %s (state %d)\n",
-		       xendev->nodename, xendev->state);
+		       "to device: %s (local state %d, remote state %d)\n",
+		       xendev->nodename, xendev->state, rstate);
 	}
 
 	return 0;
@@ -897,7 +901,7 @@ static int print_device_status(struct device *dev, void *data)
 static int ready_to_wait_for_devices;
 
 /*
- * On a 10 second timeout, wait for all devices currently configured.  We need
+ * On a 5-minute timeout, wait for all devices currently configured.  We need
  * to do this to guarantee that the filesystems and / or network devices
  * needed for boot are available, before we can allow the boot to proceed.
  *
@@ -912,18 +916,30 @@ static int ready_to_wait_for_devices;
  */
 static void wait_for_devices(struct xenbus_driver *xendrv)
 {
-	unsigned long timeout = jiffies + 10*HZ;
+	unsigned long start = jiffies;
 	struct device_driver *drv = xendrv ? &xendrv->driver : NULL;
+	unsigned int seconds_waited = 0;
 
 	if (!ready_to_wait_for_devices || !xen_domain())
 		return;
 
-	while (exists_disconnected_device(drv)) {
-		if (time_after(jiffies, timeout))
-			break;
+	while (exists_connecting_device(drv)) {
+		if (time_after(jiffies, start + (seconds_waited+5)*HZ)) {
+			if (!seconds_waited)
+				printk(KERN_WARNING "XENBUS: Waiting for "
+				       "devices to initialise: ");
+			seconds_waited += 5;
+			printk("%us...", 300 - seconds_waited);
+			if (seconds_waited == 300)
+				break;
+		}
+
 		schedule_timeout_interruptible(HZ/10);
 	}
 
+	if (seconds_waited)
+		printk("\n");
+
 	bus_for_each_dev(&xenbus_frontend.bus, NULL, drv,
 			 print_device_status);
 }