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

* 'upstream/xen' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: (23 commits)
  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
  Introduce CONFIG_XEN_PVHVM compile option
  blkfront: do not create a PV cdrom device if xen_hvm_guest
  support multiple .discard.* sections to avoid section type conflicts
  xen/pvhvm: fix build problem when !CONFIG_XEN
  xenfs: enable for HVM domains too
  x86: Call HVMOP_pagetable_dying on exit_mmap.
  x86: Unplug emulated disks and nics.
  x86: Use xen_vcpuop_clockevent, xen_clocksource and xen wallclock.
  implement O_NONBLOCK for /proc/xen/xenbus
  xen: Fix find_unbound_irq in presence of ioapic irqs.
  xen: Add suspend/resume support for PV on HVM guests.
  xen: Xen PCI platform device driver.
  x86/xen: event channels delivery on HVM.
  x86: early PV on HVM features initialization.
  xen: Add support for HVM hypercalls.
  ...

Documentation/kernel-parameters.txt

@@ -116,6 +116,7 @@ parameter is applicable:
 			More X86-64 boot options can be found in
 			Documentation/x86/x86_64/boot-options.txt .
 	X86	Either 32bit or 64bit x86 (same as X86-32+X86-64)
+	XEN	Xen support is enabled
 
 In addition, the following text indicates that the option:
 
@@ -2886,6 +2887,16 @@ and is between 256 and 4096 characters. It is defined in the file
 	xd=		[HW,XT] Original XT pre-IDE (RLL encoded) disks.
 	xd_geo=		See header of drivers/block/xd.c.
 
+	xen_emul_unplug=		[HW,X86,XEN]
+			Unplug Xen emulated devices
+			Format: [unplug0,][unplug1]
+			ide-disks -- unplug primary master IDE devices
+			aux-ide-disks -- unplug non-primary-master IDE devices
+			nics -- unplug network devices
+			all -- unplug all emulated devices (NICs and IDE disks)
+			ignore -- continue loading the Xen platform PCI driver even
+				if the version check failed
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

arch/x86/include/asm/hypervisor.h

@@ -45,5 +45,6 @@ extern const struct hypervisor_x86 *x86_hyper;
 /* Recognized hypervisors */
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
+extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 
 #endif

arch/x86/include/asm/irq_vectors.h

@@ -125,6 +125,9 @@
  */
 #define MCE_SELF_VECTOR			0xeb
 
+/* Xen vector callback to receive events in a HVM domain */
+#define XEN_HVM_EVTCHN_CALLBACK		0xe9
+
 #define NR_VECTORS			 256
 
 #define FPU_IRQ				  13

arch/x86/include/asm/setup.h

@@ -82,7 +82,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard) __used				\
+	static void __section(.discard.text) __used			\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \

arch/x86/include/asm/xen/hypercall.h

@@ -417,6 +417,12 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
 	return _hypercall2(int, nmi_op, op, arg);
 }
 
+static inline unsigned long __must_check
+HYPERVISOR_hvm_op(int op, void *arg)
+{
+       return _hypercall2(unsigned long, hvm_op, op, arg);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {

arch/x86/kernel/cpu/hypervisor.c

@@ -34,6 +34,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
 	&x86_hyper_vmware,
 	&x86_hyper_ms_hyperv,
+#ifdef CONFIG_XEN_PVHVM
+	&x86_hyper_xen_hvm,
+#endif
 };
 
 const struct hypervisor_x86 *x86_hyper;

arch/x86/kernel/entry_32.S

@@ -1166,6 +1166,9 @@ ENTRY(xen_failsafe_callback)
 .previous
 ENDPROC(xen_failsafe_callback)
 
+BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK,
+		xen_evtchn_do_upcall)
+
 #endif	/* CONFIG_XEN */
 
 #ifdef CONFIG_FUNCTION_TRACER

arch/x86/kernel/entry_64.S

@@ -1329,6 +1329,9 @@ ENTRY(xen_failsafe_callback)
 	CFI_ENDPROC
 END(xen_failsafe_callback)
 
+apicinterrupt XEN_HVM_EVTCHN_CALLBACK \
+	xen_hvm_callback_vector xen_evtchn_do_upcall
+
 #endif /* CONFIG_XEN */
 
 /*

arch/x86/xen/Kconfig

@@ -13,6 +13,11 @@ config XEN
 	  kernel to boot in a paravirtualized environment under the
 	  Xen hypervisor.
 
+config XEN_PVHVM
+	def_bool y
+	depends on XEN
+	depends on X86_LOCAL_APIC
+
 config XEN_MAX_DOMAIN_MEMORY
        int "Maximum allowed size of a domain in gigabytes"
        default 8 if X86_32

arch/x86/xen/Makefile

@@ -12,7 +12,7 @@ CFLAGS_mmu.o			:= $(nostackp)
 
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
-			grant-table.o suspend.o
+			grant-table.o suspend.o platform-pci-unplug.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o

arch/x86/xen/enlighten.c

@@ -11,6 +11,7 @@
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/smp.h>
@@ -35,8 +36,10 @@
 #include <xen/interface/version.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
+#include <xen/interface/memory.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/hvm.h>
 #include <xen/hvc-console.h>
 
 #include <asm/paravirt.h>
@@ -55,7 +58,9 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/stackprotector.h>
+#include <asm/hypervisor.h>
 
 #include "xen-ops.h"
 #include "mmu.h"
@@ -76,6 +81,10 @@ struct shared_info xen_dummy_shared_info;
 
 void *xen_initial_gdt;
 
+RESERVE_BRK(shared_info_page_brk, PAGE_SIZE);
+__read_mostly int xen_have_vector_callback;
+EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+
 /*
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
@@ -97,6 +106,14 @@ 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 +121,17 @@ 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)
-		return;		/* already tested, not available */
+	if (cpu < MAX_VIRT_CPUS)
+		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 +146,7 @@ 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 +753,6 @@ static void set_xen_basic_apic_ops(void)
 
 #endif
 
-
 static void xen_clts(void)
 {
 	struct multicall_space mcs;
@@ -926,10 +947,6 @@ static const struct pv_init_ops xen_init_ops __initdata = {
 	.patch = xen_patch,
 };
 
-static const struct pv_time_ops xen_time_ops __initdata = {
-	.sched_clock = xen_sched_clock,
-};
-
 static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.cpuid = xen_cpuid,
 
@@ -1028,6 +1045,23 @@ 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,
@@ -1067,7 +1101,6 @@ asmlinkage void __init xen_start_kernel(void)
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
-	pv_time_ops = xen_time_ops;
 	pv_cpu_ops = xen_cpu_ops;
 	pv_apic_ops = xen_apic_ops;
 
@@ -1075,13 +1108,7 @@ asmlinkage void __init xen_start_kernel(void)
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
-	x86_init.timers.timer_init = xen_time_init;
-	x86_init.timers.setup_percpu_clockev = x86_init_noop;
-	x86_cpuinit.setup_percpu_clockev = x86_init_noop;
-
-	x86_platform.calibrate_tsc = xen_tsc_khz;
-	x86_platform.get_wallclock = xen_get_wallclock;
-	x86_platform.set_wallclock = xen_set_wallclock;
+	xen_init_time_ops();
 
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
@@ -1206,3 +1233,139 @@ asmlinkage void __init xen_start_kernel(void)
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }
+
+static uint32_t xen_cpuid_base(void)
+{
+	uint32_t base, eax, ebx, ecx, edx;
+	char signature[13];
+
+	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+		cpuid(base, &eax, &ebx, &ecx, &edx);
+		*(uint32_t *)(signature + 0) = ebx;
+		*(uint32_t *)(signature + 4) = ecx;
+		*(uint32_t *)(signature + 8) = edx;
+		signature[12] = 0;
+
+		if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
+			return base;
+	}
+
+	return 0;
+}
+
+static int init_hvm_pv_info(int *major, int *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);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	xen_setup_features();
+
+	pv_info = xen_info;
+	pv_info.kernel_rpl = 0;
+
+	xen_domain_type = XEN_HVM_DOMAIN;
+
+	return 0;
+}
+
+void 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 = __pa(shared_info_page) >> PAGE_SHIFT;
+	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
+		BUG();
+
+	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.
+	 * 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];
+	}
+}
+
+#ifdef CONFIG_XEN_PVHVM
+static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	switch (action) {
+	case CPU_UP_PREPARE:
+		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = {
+	.notifier_call	= xen_hvm_cpu_notify,
+};
+
+static void __init xen_hvm_guest_init(void)
+{
+	int r;
+	int major, minor;
+
+	r = init_hvm_pv_info(&major, &minor);
+	if (r < 0)
+		return;
+
+	xen_hvm_init_shared_info();
+
+	if (xen_feature(XENFEAT_hvm_callback_vector))
+		xen_have_vector_callback = 1;
+	register_cpu_notifier(&xen_hvm_cpu_notifier);
+	xen_unplug_emulated_devices();
+	have_vcpu_info_placement = 0;
+	x86_init.irqs.intr_init = xen_init_IRQ;
+	xen_hvm_init_time_ops();
+	xen_hvm_init_mmu_ops();
+}
+
+static bool __init xen_hvm_platform(void)
+{
+	if (xen_pv_domain())
+		return false;
+
+	if (!xen_cpuid_base())
+		return false;
+
+	return true;
+}
+
+const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = {
+	.name			= "Xen HVM",
+	.detect			= xen_hvm_platform,
+	.init_platform		= xen_hvm_guest_init,
+};
+EXPORT_SYMBOL(x86_hyper_xen_hvm);
+#endif

arch/x86/xen/mmu.c

@@ -58,6 +58,7 @@
 
 #include <xen/page.h>
 #include <xen/interface/xen.h>
+#include <xen/interface/hvm/hvm_op.h>
 #include <xen/interface/version.h>
 #include <xen/hvc-console.h>
 
@@ -1941,6 +1942,40 @@ void __init xen_init_mmu_ops(void)
 	pv_mmu_ops = xen_mmu_ops;
 }
 
+#ifdef CONFIG_XEN_PVHVM
+static void xen_hvm_exit_mmap(struct mm_struct *mm)
+{
+	struct xen_hvm_pagetable_dying a;
+	int rc;
+
+	a.domid = DOMID_SELF;
+	a.gpa = __pa(mm->pgd);
+	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
+	WARN_ON_ONCE(rc < 0);
+}
+
+static int is_pagetable_dying_supported(void)
+{
+	struct xen_hvm_pagetable_dying a;
+	int rc = 0;
+
+	a.domid = DOMID_SELF;
+	a.gpa = 0x00;
+	rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a);
+	if (rc < 0) {
+		printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n");
+		return 0;
+	}
+	return 1;
+}
+
+void __init xen_hvm_init_mmu_ops(void)
+{
+	if (is_pagetable_dying_supported())
+		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+}
+#endif
+
 #ifdef CONFIG_XEN_DEBUG_FS
 
 static struct dentry *d_mmu_debug;

arch/x86/xen/mmu.h

@@ -60,4 +60,5 @@ void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 unsigned long xen_read_cr2_direct(void);
 
 extern void xen_init_mmu_ops(void);
+extern void xen_hvm_init_mmu_ops(void);
 #endif	/* _XEN_MMU_H */

arch/x86/xen/platform-pci-unplug.c

@@ -0,0 +1,137 @@
+/******************************************************************************
+ * platform-pci-unplug.c
+ *
+ * Xen platform PCI device driver
+ * Copyright (c) 2010, Citrix
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+
+#include <xen/platform_pci.h>
+
+#define XEN_PLATFORM_ERR_MAGIC -1
+#define XEN_PLATFORM_ERR_PROTOCOL -2
+#define XEN_PLATFORM_ERR_BLACKLIST -3
+
+/* store the value of xen_emul_unplug after the unplug is done */
+int xen_platform_pci_unplug;
+EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
+#ifdef CONFIG_XEN_PVHVM
+static int xen_emul_unplug;
+
+static int __init check_platform_magic(void)
+{
+	short magic;
+	char protocol;
+
+	magic = inw(XEN_IOPORT_MAGIC);
+	if (magic != XEN_IOPORT_MAGIC_VAL) {
+		printk(KERN_ERR "Xen Platform PCI: unrecognised magic value\n");
+		return XEN_PLATFORM_ERR_MAGIC;
+	}
+
+	protocol = inb(XEN_IOPORT_PROTOVER);
+
+	printk(KERN_DEBUG "Xen Platform PCI: I/O protocol version %d\n",
+			protocol);
+
+	switch (protocol) {
+	case 1:
+		outw(XEN_IOPORT_LINUX_PRODNUM, XEN_IOPORT_PRODNUM);
+		outl(XEN_IOPORT_LINUX_DRVVER, XEN_IOPORT_DRVVER);
+		if (inw(XEN_IOPORT_MAGIC) != XEN_IOPORT_MAGIC_VAL) {
+			printk(KERN_ERR "Xen Platform: blacklisted by host\n");
+			return XEN_PLATFORM_ERR_BLACKLIST;
+		}
+		break;
+	default:
+		printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version");
+		return XEN_PLATFORM_ERR_PROTOCOL;
+	}
+
+	return 0;
+}
+
+void __init xen_unplug_emulated_devices(void)
+{
+	int r;
+
+	/* check the version of the xen platform PCI device */
+	r = check_platform_magic();
+	/* If the version matches enable the Xen platform PCI driver.
+	 * Also enable the Xen platform PCI driver if the version is really old
+	 * and the user told us to ignore it. */
+	if (r && !(r == XEN_PLATFORM_ERR_MAGIC &&
+			(xen_emul_unplug & XEN_UNPLUG_IGNORE)))
+		return;
+	/* Set the default value of xen_emul_unplug depending on whether or
+	 * not the Xen PV frontends and the Xen platform PCI driver have
+	 * been compiled for this kernel (modules or built-in are both OK). */
+	if (!xen_emul_unplug) {
+		if (xen_must_unplug_nics()) {
+			printk(KERN_INFO "Netfront and the Xen platform PCI driver have "
+					"been compiled for this kernel: unplug emulated NICs.\n");
+			xen_emul_unplug |= XEN_UNPLUG_ALL_NICS;
+		}
+		if (xen_must_unplug_disks()) {
+			printk(KERN_INFO "Blkfront and the Xen platform PCI driver have "
+					"been compiled for this kernel: unplug emulated disks.\n"
+					"You might have to change the root device\n"
+					"from /dev/hd[a-d] to /dev/xvd[a-d]\n"
+					"in your root= kernel command line option\n");
+			xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS;
+		}
+	}
+	/* Now unplug the emulated devices */
+	if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE))
+		outw(xen_emul_unplug, XEN_IOPORT_UNPLUG);
+	xen_platform_pci_unplug = xen_emul_unplug;
+}
+
+static int __init parse_xen_emul_unplug(char *arg)
+{
+	char *p, *q;
+	int l;
+
+	for (p = arg; p; p = q) {
+		q = strchr(p, ',');
+		if (q) {
+			l = q - p;
+			q++;
+		} else {
+			l = strlen(p);
+		}
+		if (!strncmp(p, "all", l))
+			xen_emul_unplug |= XEN_UNPLUG_ALL;
+		else if (!strncmp(p, "ide-disks", l))
+			xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS;
+		else if (!strncmp(p, "aux-ide-disks", l))
+			xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS;
+		else if (!strncmp(p, "nics", l))
+			xen_emul_unplug |= XEN_UNPLUG_ALL_NICS;
+		else if (!strncmp(p, "ignore", l))
+			xen_emul_unplug |= XEN_UNPLUG_IGNORE;
+		else
+			printk(KERN_WARNING "unrecognised option '%s' "
+				 "in parameter 'xen_emul_unplug'\n", p);
+	}
+	return 0;
+}
+early_param("xen_emul_unplug", parse_xen_emul_unplug);
+#endif

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/suspend.c

@@ -26,6 +26,18 @@ void xen_pre_suspend(void)
 		BUG();
 }
 
+void xen_hvm_post_suspend(int suspend_cancelled)
+{
+	int cpu;
+	xen_hvm_init_shared_info();
+	xen_callback_vector();
+	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
+		for_each_online_cpu(cpu) {
+			xen_setup_runstate_info(cpu);
+		}
+	}
+}
+
 void xen_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();

arch/x86/xen/time.c

@@ -20,6 +20,7 @@
 #include <asm/xen/hypercall.h>
 
 #include <xen/events.h>
+#include <xen/features.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/vcpu.h>
 
@@ -155,47 +156,8 @@ 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)
+static unsigned long xen_tsc_khz(void)
 {
 	struct pvclock_vcpu_time_info *info =
 		&HYPERVISOR_shared_info->vcpu_info[0].time;
@@ -230,7 +192,7 @@ static void xen_read_wallclock(struct timespec *ts)
 	put_cpu_var(xen_vcpu);
 }
 
-unsigned long xen_get_wallclock(void)
+static unsigned long xen_get_wallclock(void)
 {
 	struct timespec ts;
 
@@ -238,7 +200,7 @@ unsigned long xen_get_wallclock(void)
 	return ts.tv_sec;
 }
 
-int xen_set_wallclock(unsigned long now)
+static int xen_set_wallclock(unsigned long now)
 {
 	/* do nothing for domU */
 	return -1;
@@ -473,7 +435,11 @@ void xen_timer_resume(void)
 	}
 }
 
-__init void xen_time_init(void)
+static const struct pv_time_ops xen_time_ops __initdata = {
+	.sched_clock = xen_clocksource_read,
+};
+
+static __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
 	struct timespec tp;
@@ -497,3 +463,47 @@ __init void xen_time_init(void)
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();
 }
+
+__init void xen_init_time_ops(void)
+{
+	pv_time_ops = xen_time_ops;
+
+	x86_init.timers.timer_init = xen_time_init;
+	x86_init.timers.setup_percpu_clockev = x86_init_noop;
+	x86_cpuinit.setup_percpu_clockev = x86_init_noop;
+
+	x86_platform.calibrate_tsc = xen_tsc_khz;
+	x86_platform.get_wallclock = xen_get_wallclock;
+	x86_platform.set_wallclock = xen_set_wallclock;
+}
+
+#ifdef CONFIG_XEN_PVHVM
+static void xen_hvm_setup_cpu_clockevents(void)
+{
+	int cpu = smp_processor_id();
+	xen_setup_runstate_info(cpu);
+	xen_setup_timer(cpu);
+	xen_setup_cpu_clockevents();
+}
+
+__init void xen_hvm_init_time_ops(void)
+{
+	/* vector callback is needed otherwise we cannot receive interrupts
+	 * on cpu > 0 */
+	if (!xen_have_vector_callback && num_present_cpus() > 1)
+		return;
+	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
+		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
+				"disable pv timer\n");
+		return;
+	}
+
+	pv_time_ops = xen_time_ops;
+	x86_init.timers.setup_percpu_clockev = xen_time_init;
+	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
+
+	x86_platform.calibrate_tsc = xen_tsc_khz;
+	x86_platform.get_wallclock = xen_get_wallclock;
+	x86_platform.set_wallclock = xen_set_wallclock;
+}
+#endif

arch/x86/xen/xen-ops.h

@@ -38,6 +38,10 @@ void xen_enable_sysenter(void);
 void xen_enable_syscall(void);
 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 __init xen_build_dynamic_phys_to_machine(void);
 
 void xen_init_irq_ops(void);
@@ -46,11 +50,8 @@ 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);
-unsigned long xen_tsc_khz(void);
-void __init xen_time_init(void);
-unsigned long xen_get_wallclock(void);
-int xen_set_wallclock(unsigned long time);
-unsigned long long xen_sched_clock(void);
+void __init xen_init_time_ops(void);
+void __init xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
@@ -101,4 +102,6 @@ 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/block/xen-blkfront.c

@@ -48,6 +48,7 @@
 #include <xen/grant_table.h>
 #include <xen/events.h>
 #include <xen/page.h>
+#include <xen/platform_pci.h>
 
 #include <xen/interface/grant_table.h>
 #include <xen/interface/io/blkif.h>
@@ -737,6 +738,35 @@ static int blkfront_probe(struct xenbus_device *dev,
 		}
 	}
 
+	if (xen_hvm_domain()) {
+		char *type;
+		int len;
+		/* no unplug has been done: do not hook devices != xen vbds */
+		if (xen_platform_pci_unplug & XEN_UNPLUG_IGNORE) {
+			int major;
+
+			if (!VDEV_IS_EXTENDED(vdevice))
+				major = BLKIF_MAJOR(vdevice);
+			else
+				major = XENVBD_MAJOR;
+
+			if (major != XENVBD_MAJOR) {
+				printk(KERN_INFO
+						"%s: HVM does not support vbd %d as xen block device\n",
+						__FUNCTION__, vdevice);
+				return -ENODEV;
+			}
+		}
+		/* do not create a PV cdrom device if we are an HVM guest */
+		type = xenbus_read(XBT_NIL, dev->nodename, "device-type", &len);
+		if (IS_ERR(type))
+			return -ENODEV;
+		if (strncmp(type, "cdrom", 5) == 0) {
+			kfree(type);
+			return -ENODEV;
+		}
+		kfree(type);
+	}
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure");