Merge branch 'upstream/pvhvm' into upstream/xen

* upstream/pvhvm:
  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.
  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.

Conflicts:
	arch/x86/xen/enlighten.c
	arch/x86/xen/time.c

Documentation/kernel-parameters.txt

@@ -115,6 +115,7 @@ 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:
 
@@ -2879,6 +2880,16 @@ 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.
@@ -938,10 +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_clocksource_read,
-};
-
 static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.cpuid = xen_cpuid,
 
@@ -1096,21 +1101,14 @@ 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;
 
 	x86_init.resources.memory_setup = xen_memory_setup;
 	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.
@@ -1235,3 +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 */