1 files changed, 118 insertions, 20 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index fa6ade76ef3f..201d09a7c46b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -262,8 +262,9 @@ 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);
+        pr_info("Booting paravirtualized kernel %son %s\n",
+                xen_feature(XENFEAT_auto_translated_physmap) ?
+                        "with PVH extensions " : "", 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)" : "");
@@ -433,7 +434,7 @@ static void __init xen_init_cpuid_mask(void)
 
         ax = 1;
         cx = 0;
-        xen_cpuid(&ax, &bx, &cx, &dx);
+        cpuid(1, &ax, &bx, &cx, &dx);
 
         xsave_mask =
                 (1 << (X86_FEATURE_XSAVE % 32)) |
@@ -1142,8 +1143,9 @@ 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 */
-        if (have_vcpu_info_placement) {
+         * 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()) {
                 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);
@@ -1407,9 +1409,49 @@ 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 __init xen_setup_stackprotector(void)
+static void __ref 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;
 
@@ -1420,6 +1462,58 @@ static void __init xen_setup_stackprotector(void)
         pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
+/*
+ * 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.
+        */
+        if (cpu_has_pse)
+                set_in_cr4(X86_CR4_PSE);
+
+        if (cpu_has_pge)
+                set_in_cr4(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;
+
+        if (!xen_feature(XENFEAT_hvm_callback_vector))
+                return;
+
+        xen_have_vector_callback = 1;
+        xen_pvh_set_cr_flags(0);
+
+#ifdef CONFIG_X86_32
+        BUG(); /* PVH: Implement proper support. */
+#endif
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
@@ -1431,13 +1525,16 @@ asmlinkage void __init xen_start_kernel(void)
 
         xen_domain_type = XEN_PV_DOMAIN;
 
+        xen_setup_features();
+        xen_pvh_early_guest_init();
         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 = xen_cpu_ops;
 
         x86_init.resources.memory_setup = xen_memory_setup;
         x86_init.oem.arch_setup = xen_arch_setup;
@@ -1469,17 +1566,14 @@ 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();
+        xen_build_dynamic_phys_to_machine();
 
         /*
          * Set up kernel GDT and segment registers, mainly so that
          * -fstack-protector code can be executed.
          */
-        xen_setup_stackprotector();
+        xen_setup_gdt(0);
 
         xen_init_irq_ops();
         xen_init_cpuid_mask();
@@ -1548,14 +1642,18 @@ asmlinkage void __init xen_start_kernel(void)
         /* set the limit of our address space */
         xen_reserve_top();
 
-        /* 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);
+        /* 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);
+        }
 
 #ifdef CONFIG_X86_32
         /* set up basic CPUID stuff */