1 files changed, 148 insertions, 131 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 51ef95232725..ec1d5c46e58f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -45,6 +45,7 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/nmi.h>
 #include <xen/interface/xen-mca.h>
+#include <xen/interface/hvm/start_info.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/hvm.h>
@@ -176,6 +177,20 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
+#ifdef CONFIG_XEN_PVH
+/*
+ * PVH variables.
+ *
+ * xen_pvh and pvh_bootparams need to live in data segment since they
+ * are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+bool xen_pvh __attribute__((section(".data"))) = 0;
+struct boot_params pvh_bootparams __attribute__((section(".data")));
+
+struct hvm_start_info pvh_start_info;
+unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+#endif
+
 static void clamp_max_cpus(void)
 {
 #ifdef CONFIG_SMP
@@ -1138,10 +1153,11 @@ void xen_setup_vcpu_info_placement(void)
 		xen_vcpu_setup(cpu);
 	}
 
-	/* xen_vcpu_setup managed to place the vcpu_info within the
-	 * percpu area for all cpus, so make use of it. Note that for
-	 * PVH we want to use native IRQ mechanism. */
-	if (have_vcpu_info_placement && !xen_pvh_domain()) {
+	/*
+	 * xen_vcpu_setup managed to place the vcpu_info within the
+	 * percpu area for all cpus, so make use of it.
+	 */
+	if (have_vcpu_info_placement) {
 		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
 		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
@@ -1413,49 +1429,9 @@ static void __init xen_boot_params_init_edd(void)
  * Set up the GDT and segment registers for -fstack-protector.  Until
  * we do this, we have to be careful not to call any stack-protected
  * function, which is most of the kernel.
- *
- * Note, that it is __ref because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
  */
-static void __ref xen_setup_gdt(int cpu)
+static void xen_setup_gdt(int cpu)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_X86_64
-		unsigned long dummy;
-
-		load_percpu_segment(cpu); /* We need to access per-cpu area */
-		switch_to_new_gdt(cpu); /* GDT and GS set */
-
-		/* We are switching of the Xen provided GDT to our HVM mode
-		 * GDT. The new GDT has  __KERNEL_CS with CS.L = 1
-		 * and we are jumping to reload it.
-		 */
-		asm volatile ("pushq %0\n"
-			      "leaq 1f(%%rip),%0\n"
-			      "pushq %0\n"
-			      "lretq\n"
-			      "1:\n"
-			      : "=&r" (dummy) : "0" (__KERNEL_CS));
-
-		/*
-		 * While not needed, we also set the %es, %ds, and %fs
-		 * to zero. We don't care about %ss as it is NULL.
-		 * Strictly speaking this is not needed as Xen zeros those
-		 * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE)
-		 *
-		 * Linux zeros them in cpu_init() and in secondary_startup_64
-		 * (for BSP).
-		 */
-		loadsegment(es, 0);
-		loadsegment(ds, 0);
-		loadsegment(fs, 0);
-#else
-		/* PVH: TODO Implement. */
-		BUG();
-#endif
-		return; /* PVH does not need any PV GDT ops. */
-	}
 	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
 
@@ -1466,59 +1442,6 @@ static void __ref xen_setup_gdt(int cpu)
 	pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
-#ifdef CONFIG_XEN_PVH
-/*
- * A PV guest starts with default flags that are not set for PVH, set them
- * here asap.
- */
-static void xen_pvh_set_cr_flags(int cpu)
-{
-
-	/* Some of these are setup in 'secondary_startup_64'. The others:
-	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
-	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
-	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
-
-	if (!cpu)
-		return;
-	/*
-	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
-	*/
-	if (boot_cpu_has(X86_FEATURE_PSE))
-		cr4_set_bits_and_update_boot(X86_CR4_PSE);
-
-	if (boot_cpu_has(X86_FEATURE_PGE))
-		cr4_set_bits_and_update_boot(X86_CR4_PGE);
-}
-
-/*
- * Note, that it is ref - because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
- */
-void __ref xen_pvh_secondary_vcpu_init(int cpu)
-{
-	xen_setup_gdt(cpu);
-	xen_pvh_set_cr_flags(cpu);
-}
-
-static void __init xen_pvh_early_guest_init(void)
-{
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
-
-	xen_pvh_early_cpu_init(0, false);
-	xen_pvh_set_cr_flags(0);
-
-#ifdef CONFIG_X86_32
-	BUG(); /* PVH: Implement proper support. */
-#endif
-}
-#endif    /* CONFIG_XEN_PVH */
-
 static void __init xen_dom0_set_legacy_features(void)
 {
 	x86_platform.legacy.rtc = 1;
@@ -1555,24 +1478,17 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_domain_type = XEN_PV_DOMAIN;
 
 	xen_setup_features();
-#ifdef CONFIG_XEN_PVH
-	xen_pvh_early_guest_init();
-#endif
+
 	xen_setup_machphys_mapping();
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
-	if (!xen_pvh_domain()) {
-		pv_cpu_ops = xen_cpu_ops;
+	pv_cpu_ops = xen_cpu_ops;
 
-		x86_platform.get_nmi_reason = xen_get_nmi_reason;
-	}
+	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
-	else
-		x86_init.resources.memory_setup = xen_memory_setup;
+	x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
@@ -1665,18 +1581,15 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* set the limit of our address space */
 	xen_reserve_top();
 
-	/* PVH: runs at default kernel iopl of 0 */
-	if (!xen_pvh_domain()) {
-		/*
-		 * We used to do this in xen_arch_setup, but that is too late
-		 * on AMD were early_cpu_init (run before ->arch_setup()) calls
-		 * early_amd_init which pokes 0xcf8 port.
-		 */
-		set_iopl.iopl = 1;
-		rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-		if (rc != 0)
-			xen_raw_printk("physdev_op failed %d\n", rc);
-	}
+	/*
+	 * We used to do this in xen_arch_setup, but that is too late
+	 * on AMD were early_cpu_init (run before ->arch_setup()) calls
+	 * early_amd_init which pokes 0xcf8 port.
+	 */
+	set_iopl.iopl = 1;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+	if (rc != 0)
+		xen_raw_printk("physdev_op failed %d\n", rc);
 
 #ifdef CONFIG_X86_32
 	/* set up basic CPUID stuff */
@@ -1758,6 +1671,102 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 }
 
+#ifdef CONFIG_XEN_PVH
+
+static void xen_pvh_arch_setup(void)
+{
+#ifdef CONFIG_ACPI
+	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
+	if (nr_ioapics == 0)
+		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
+#endif
+}
+
+static void __init init_pvh_bootparams(void)
+{
+	struct xen_memory_map memmap;
+	unsigned int i;
+	int rc;
+
+	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map);
+	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map);
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc) {
+		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
+		BUG();
+	}
+
+	if (memmap.nr_entries < E820MAX - 1) {
+		pvh_bootparams.e820_map[memmap.nr_entries].addr =
+			ISA_START_ADDRESS;
+		pvh_bootparams.e820_map[memmap.nr_entries].size =
+			ISA_END_ADDRESS - ISA_START_ADDRESS;
+		pvh_bootparams.e820_map[memmap.nr_entries].type =
+			E820_RESERVED;
+		memmap.nr_entries++;
+	} else
+		xen_raw_printk("Warning: Can fit ISA range into e820\n");
+
+	sanitize_e820_map(pvh_bootparams.e820_map,
+			  ARRAY_SIZE(pvh_bootparams.e820_map),
+			  &memmap.nr_entries);
+
+	pvh_bootparams.e820_entries = memmap.nr_entries;
+	for (i = 0; i < pvh_bootparams.e820_entries; i++)
+		e820_add_region(pvh_bootparams.e820_map[i].addr,
+				pvh_bootparams.e820_map[i].size,
+				pvh_bootparams.e820_map[i].type);
+
+	pvh_bootparams.hdr.cmd_line_ptr =
+		pvh_start_info.cmdline_paddr;
+
+	/* The first module is always ramdisk. */
+	if (pvh_start_info.nr_modules) {
+		struct hvm_modlist_entry *modaddr =
+			__va(pvh_start_info.modlist_paddr);
+		pvh_bootparams.hdr.ramdisk_image = modaddr->paddr;
+		pvh_bootparams.hdr.ramdisk_size = modaddr->size;
+	}
+
+	/*
+	 * See Documentation/x86/boot.txt.
+	 *
+	 * Version 2.12 supports Xen entry point but we will use default x86/PC
+	 * environment (i.e. hardware_subarch 0).
+	 */
+	pvh_bootparams.hdr.version = 0x212;
+	pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+}
+
+/*
+ * This routine (and those that it might call) should not use
+ * anything that lives in .bss since that segment will be cleared later.
+ */
+void __init xen_prepare_pvh(void)
+{
+	u32 msr;
+	u64 pfn;
+
+	if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
+		xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
+				pvh_start_info.magic);
+		BUG();
+	}
+
+	xen_pvh = 1;
+
+	msr = cpuid_ebx(xen_cpuid_base() + 2);
+	pfn = __pa(hypercall_page);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	init_pvh_bootparams();
+
+	x86_init.oem.arch_setup = xen_pvh_arch_setup;
+}
+#endif
+
 void __ref xen_hvm_init_shared_info(void)
 {
 	int cpu;
@@ -1797,20 +1806,29 @@ void __ref xen_hvm_init_shared_info(void)
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
-	uint32_t eax, ebx, ecx, edx, pages, msr, base;
-	u64 pfn;
+	uint32_t eax, ebx, ecx, edx, base;
 
 	base = xen_cpuid_base();
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+	eax = cpuid_eax(base + 1);
 
 	major = eax >> 16;
 	minor = eax & 0xffff;
 	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
 
-	cpuid(base + 2, &pages, &msr, &ecx, &edx);
+	xen_domain_type = XEN_HVM_DOMAIN;
 
-	pfn = __pa(hypercall_page);
-	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+	/* PVH set up hypercall page in xen_prepare_pvh(). */
+	if (xen_pvh_domain())
+		pv_info.name = "Xen PVH";
+	else {
+		u64 pfn;
+		uint32_t msr;
+
+		pv_info.name = "Xen HVM";
+		msr = cpuid_ebx(base + 2);
+		pfn = __pa(hypercall_page);
+		wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+	}
 
 	xen_setup_features();
 
@@ -1819,10 +1837,6 @@ static void __init init_hvm_pv_info(void)
 		this_cpu_write(xen_vcpu_id, ebx);
 	else
 		this_cpu_write(xen_vcpu_id, smp_processor_id());
-
-	pv_info.name = "Xen HVM";
-
-	xen_domain_type = XEN_HVM_DOMAIN;
 }
 #endif
 
@@ -1910,6 +1924,9 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+
+	if (xen_pvh_domain())
+		machine_ops.emergency_restart = xen_emergency_restart;
 #ifdef CONFIG_KEXEC_CORE
 	machine_ops.shutdown = xen_hvm_shutdown;
 	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;