[[RFC PATCH 2/8]: PVH: changes related to initial boot and irq rewiring

[Mukesh Rathor <mukesh.rathor@oracle.com>]

---
 arch/x86/xen/enlighten.c |   67 ++++++++++++++++++++++++++++++++++++++-------
 arch/x86/xen/irq.c       |   22 ++++++++++++++-
 2 files changed, 77 insertions(+), 12 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bf4bda6..3a58c51 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -139,6 +139,8 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
+static void __init xen_hvm_init_shared_info(void);
+
 static void clamp_max_cpus(void)
 {
 #ifdef CONFIG_SMP
@@ -217,8 +219,8 @@ static void __init xen_banner(void)
 	struct xen_extraversion extra;
 	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
 
-	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
-	       pv_info.name);
+	printk(KERN_INFO "Booting paravirtualized kernel %son %s\n",
+		(xen_pvh_domain() ? "in HVM " : ""), pv_info.name);
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
@@ -271,12 +273,15 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		break;
 	}
 
-	asm(XEN_EMULATE_PREFIX "cpuid"
-		: "=a" (*ax),
-		  "=b" (*bx),
-		  "=c" (*cx),
-		  "=d" (*dx)
-		: "0" (*ax), "2" (*cx));
+	if (xen_pvh_domain())
+		native_cpuid(ax, bx, cx, dx);
+	else
+		asm(XEN_EMULATE_PREFIX "cpuid"
+			: "=a" (*ax),
+			"=b" (*bx),
+			"=c" (*cx),
+			"=d" (*dx)
+			: "0" (*ax), "2" (*cx));
 
 	*bx &= maskebx;
 	*cx &= maskecx;
@@ -1034,6 +1039,10 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 
 void xen_setup_shared_info(void)
 {
+	/* do later in xen_pvh_guest_init() when extend_brk is properly setup*/
+	if (xen_pvh_domain() && xen_initial_domain())
+		return;
+
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		set_fixmap(FIX_PARAVIRT_BOOTMAP,
 			   xen_start_info->shared_info);
@@ -1044,6 +1053,10 @@ void xen_setup_shared_info(void)
 		HYPERVISOR_shared_info =
 			(struct shared_info *)__va(xen_start_info->shared_info);
 
+	/* PVH TBD/FIXME: vcpu info placement in phase 2 */
+	if (xen_pvh_domain())
+		return;
+
 #ifndef CONFIG_SMP
 	/* In UP this is as good a place as any to set up shared info */
 	xen_setup_vcpu_info_placement();
@@ -1274,6 +1287,10 @@ static const struct machine_ops xen_machine_ops __initconst = {
  */
 static void __init xen_setup_stackprotector(void)
 {
+	if (xen_pvh_domain()) {
+		switch_to_new_gdt(0);
+		return;
+	}
 	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
 
@@ -1284,6 +1301,25 @@ static void __init xen_setup_stackprotector(void)
 	pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
+static void __init xen_pvh_guest_init(void)
+{
+#ifndef __HAVE_ARCH_PTE_SPECIAL
+	("__HAVE_ARCH_PTE_SPECIAL is required for PVH for now\n");
+	#error("__HAVE_ARCH_PTE_SPECIAL is required for PVH\n");
+#endif
+	/* PVH TBD/FIXME: for now just disable this. */
+	have_vcpu_info_placement = 0;
+
+	if (xen_feature(XENFEAT_hvm_callback_vector))
+		xen_have_vector_callback = 1;
+
+        /* for domU, the library sets start_info.shared_info to pfn, but for
+         * dom0, it contains mfn. we need to get the pfn for shared_info. PVH
+	 * uses HVM code in many places */
+	if (xen_initial_domain())
+		xen_hvm_init_shared_info();
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
@@ -1294,15 +1330,23 @@ asmlinkage void __init xen_start_kernel(void)
 	if (!xen_start_info)
 		return;
 
+#ifdef CONFIG_X86_32
+	xen_raw_printk("ERROR: 32bit PV guest can not run in HVM container\n");
+	return;
+#endif
 	xen_domain_type = XEN_PV_DOMAIN;
 
+	xen_setup_features();
 	xen_setup_machphys_mapping();
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
-	pv_cpu_ops = xen_cpu_ops;
 	pv_apic_ops = xen_apic_ops;
+	if (xen_pvh_domain())
+		pv_cpu_ops.cpuid = xen_cpuid;
+	else
+		pv_cpu_ops = xen_cpu_ops;
 
 	x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
@@ -1334,8 +1378,6 @@ asmlinkage void __init xen_start_kernel(void)
 	/* Work out if we support NX */
 	x86_configure_nx();
 
-	xen_setup_features();
-
 	/* Get mfn list */
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
 		xen_build_dynamic_phys_to_machine();
@@ -1462,6 +1504,9 @@ asmlinkage void __init xen_start_kernel(void)
 
 	xen_setup_runstate_info(0);
 
+	if (xen_pvh_domain())
+		xen_pvh_guest_init();
+
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 1573376..7c7dfd1 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -100,6 +100,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
 
 static void xen_safe_halt(void)
 {
+	/* so event channel can be delivered to us, since in HVM container */
+	if (xen_pvh_domain())
+		local_irq_enable();
+
 	/* Blocking includes an implicit local_irq_enable(). */
 	if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)
 		BUG();
@@ -126,8 +130,24 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
 #endif
 };
 
+static const struct pv_irq_ops xen_pvh_irq_ops __initdata = {
+	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+	.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+	.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
+
+	.safe_halt = xen_safe_halt,
+	.halt = xen_halt,
+#ifdef CONFIG_X86_64
+	.adjust_exception_frame = paravirt_nop,
+#endif
+};
+
 void __init xen_init_irq_ops(void)
 {
-	pv_irq_ops = xen_irq_ops;
+	if (xen_pvh_domain())
+		pv_irq_ops = xen_pvh_irq_ops;
+	else
+		pv_irq_ops = xen_irq_ops;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 }
-- 
1.7.2.3