1 files changed, 184 insertions, 17 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 65d8d79b46a8..7d46c8441418 100644
--- a/arch/x86/xen/enlighten.c
+++ b/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];
 
-	vcpup = &per_cpu(xen_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.
@@ -1145,6 +1172,10 @@ asmlinkage void __init xen_start_kernel(void)
 
 	pgd = (pgd_t *)xen_start_info->pt_base;
 
+	if (!xen_initial_domain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
+	__supported_pte_mask |= _PAGE_IOMAP;
 	/* Don't do the full vcpu_info placement stuff until we have a
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
@@ -1206,3 +1237,139 @@ 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