xen/pvh: Bootstrap PVH guest

Start PVH guest at XEN_ELFNOTE_PHYS32_ENTRY address. Setup hypercall
page, initialize boot_params, enable early page tables.

Since this stub is executed before kernel entry point we cannot use
variables in .bss which is cleared by kernel. We explicitly place
variables that are initialized here into .data.

While adjusting xen_hvm_init_shared_info() make it use cpuid_e?x()
instead of cpuid() (wherever possible).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>

1 files changed, 114 insertions, 10 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 828f1b226f56..d2144f7c8fab 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
@@ -1656,6 +1671,90 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 }
 
+#ifdef CONFIG_XEN_PVH
+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();
+}
+#endif
+
 void __ref xen_hvm_init_shared_info(void)
 {
 	int cpu;
@@ -1695,20 +1794,29 @@ 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();
 
@@ -1717,10 +1825,6 @@ 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