Merge branch 'upstream/core' into upstream/xen

* upstream/core:
  xen/panic: use xen_reboot and fix smp_send_stop
  Xen: register panic notifier to take crashes of xen guests on panic
  xen: support large numbers of CPUs with vcpu info placement
  xen: drop xen_sched_clock in favour of using plain wallclock time
  pvops: do not notify callers from register_xenstore_notifier
  xen: make sure pages are really part of domain before freeing
  xen: release unused free memory

arch/x86/xen/enlighten.c

@@ -97,6 +97,14 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
  */
 static int have_vcpu_info_placement = 1;
 
+static void clamp_max_cpus(void)
+{
+#ifdef CONFIG_SMP
+	if (setup_max_cpus > MAX_VIRT_CPUS)
+		setup_max_cpus = MAX_VIRT_CPUS;
+#endif
+}
+
 static void xen_vcpu_setup(int cpu)
 {
 	struct vcpu_register_vcpu_info info;
@@ -104,13 +112,17 @@ static void xen_vcpu_setup(int cpu)
 	struct vcpu_info *vcpup;
 
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
-	per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 
-	if (!have_vcpu_info_placement)
+	if (cpu < MAX_VIRT_CPUS)
-		return;		/* already tested, not available */
+		per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+
+	if (!have_vcpu_info_placement) {
+		if (cpu >= MAX_VIRT_CPUS)
+			clamp_max_cpus();
+		return;
+	}
 
 	vcpup = &per_cpu(xen_vcpu_info, cpu);
-
 	info.mfn = arbitrary_virt_to_mfn(vcpup);
 	info.offset = offset_in_page(vcpup);
 
@@ -125,6 +137,7 @@ static void xen_vcpu_setup(int cpu)
 	if (err) {
 		printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
 		have_vcpu_info_placement = 0;
+		clamp_max_cpus();
 	} else {
 		/* This cpu is using the registered vcpu info, even if
 		   later ones fail to. */
@@ -731,7 +744,6 @@ static void set_xen_basic_apic_ops(void)
 
 #endif
 
-
 static void xen_clts(void)
 {
 	struct multicall_space mcs;
@@ -927,7 +939,7 @@ 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 = {
@@ -1028,6 +1040,23 @@ static void xen_crash_shutdown(struct pt_regs *regs)
 	xen_reboot(SHUTDOWN_crash);
 }
 
+static int
+xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	xen_reboot(SHUTDOWN_crash);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xen_panic_block = {
+	.notifier_call= xen_panic_event,
+};
+
+int xen_panic_handler_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block);
+	return 0;
+}
+
 static const struct machine_ops __initdata xen_machine_ops = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,

arch/x86/xen/setup.c

@@ -20,6 +20,7 @@
 #include <xen/page.h>
 #include <xen/interface/callback.h>
 #include <xen/interface/physdev.h>
+#include <xen/interface/memory.h>
 #include <xen/features.h>
 
 #include "xen-ops.h"
@@ -32,6 +33,73 @@ extern void xen_sysenter_target(void);
 extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
 
+static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
+					      phys_addr_t end_addr)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = 0,
+		.domid        = DOMID_SELF
+	};
+	unsigned long start, end;
+	unsigned long len = 0;
+	unsigned long pfn;
+	int ret;
+
+	start = PFN_UP(start_addr);
+	end = PFN_DOWN(end_addr);
+
+	if (end <= start)
+		return 0;
+
+	printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ",
+	       start, end);
+	for(pfn = start; pfn < end; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
+
+		/* Make sure pfn exists to start with */
+		if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+			continue;
+
+		set_xen_guest_handle(reservation.extent_start, &mfn);
+		reservation.nr_extents = 1;
+
+		ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+					   &reservation);
+		WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
+		     start, end, ret);
+		if (ret == 1) {
+			set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+			len++;
+		}
+	}
+	printk(KERN_CONT "%ld pages freed\n", len);
+
+	return len;
+}
+
+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;
+	unsigned long released = 0;
+	int i;
+
+	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 < max_addr)
+		released += xen_release_chunk(last_end, max_addr);
+
+	printk(KERN_INFO "released %ld pages of unused memory\n", released);
+	return released;
+}
 
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
@@ -67,6 +135,8 @@ char * __init xen_memory_setup(void)
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
+	xen_return_unused_memory(xen_start_info->nr_pages, &e820);
+
 	return "Xen";
 }
 
@@ -156,6 +226,8 @@ 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);
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
 

arch/x86/xen/smp.c

@@ -394,6 +394,8 @@ static void stop_self(void *v)
 	load_cr3(swapper_pg_dir);
 	/* should set up a minimal gdt */
 
+	set_cpu_online(cpu, false);
+
 	HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL);
 	BUG();
 }

arch/x86/xen/time.c

@@ -155,45 +155,6 @@ 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)
 {

arch/x86/xen/xen-ops.h

@@ -101,4 +101,6 @@ void xen_sysret32(void);
 void xen_sysret64(void);
 void xen_adjust_exception_frame(void);
 
+extern int xen_panic_handler_init(void);
+
 #endif /* XEN_OPS_H */

drivers/xen/xenbus/xenbus_probe.c

@@ -752,10 +752,7 @@ int register_xenstore_notifier(struct notifier_block *nb)
 {
 	int ret = 0;
 
-	if (xenstored_ready > 0)
+	blocking_notifier_chain_register(&xenstore_chain, nb);
-		ret = nb->notifier_call(nb, 0, NULL);
-	else
-		blocking_notifier_chain_register(&xenstore_chain, nb);
 
 	return ret;
 }