[PATCH v1 02/12] xen/hvmlite: Factor out common kernel init code

From: Boris Ostrovsky
Date: Fri Jan 22 2016 - 16:39:44 EST


HVMlite guests (to be introduced in subsequent patches) share most
of the kernel initialization code with PV(H).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
---
arch/x86/xen/enlighten.c | 225 ++++++++++++++++++++++++----------------------
1 files changed, 119 insertions(+), 106 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d09e4c9..2cf446a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1505,19 +1505,14 @@ static void __init xen_pvh_early_guest_init(void)
}
#endif /* CONFIG_XEN_PVH */

-/* First C function to be called on Xen boot */
-asmlinkage __visible void __init xen_start_kernel(void)
+
+static void __init xen_init_kernel(void)
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
u64 pat;
int rc;

- if (!xen_start_info)
- return;
-
- xen_domain_type = XEN_PV_DOMAIN;
-
xen_setup_features();
#ifdef CONFIG_XEN_PVH
xen_pvh_early_guest_init();
@@ -1529,48 +1524,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
if (xen_initial_domain())
pv_info.features |= PV_SUPPORTED_RTC;
pv_init_ops = xen_init_ops;
- if (!xen_pvh_domain()) {
- pv_cpu_ops = xen_cpu_ops;
-
- 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.oem.arch_setup = xen_arch_setup;
- x86_init.oem.banner = xen_banner;

xen_init_time_ops();

- /*
- * Set up some pagetable state before starting to set any ptes.
- */
-
- xen_init_mmu_ops();
-
- /* Prevent unwanted bits from being set in PTEs. */
- __supported_pte_mask &= ~_PAGE_GLOBAL;
-
- /*
- * Prevent page tables from being allocated in highmem, even
- * if CONFIG_HIGHPTE is enabled.
- */
- __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
- /* Work out if we support NX */
- x86_configure_nx();
-
- /* Get mfn list */
- xen_build_dynamic_phys_to_machine();
-
- /*
- * Set up kernel GDT and segment registers, mainly so that
- * -fstack-protector code can be executed.
- */
- xen_setup_gdt(0);
-
xen_init_irq_ops();
xen_init_cpuid_mask();

@@ -1580,21 +1536,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
*/
xen_init_apic();
#endif
-
- if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
- pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
- pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
- }
-
machine_ops = xen_machine_ops;

- /*
- * The only reliable way to retain the initial address of the
- * percpu gdt_page is to remember it here, so we can go and
- * mark it RW later, when the initial percpu area is freed.
- */
- xen_initial_gdt = &per_cpu(gdt_page, 0);
-
xen_smp_init();

#ifdef CONFIG_ACPI_NUMA
@@ -1609,66 +1552,126 @@ asmlinkage __visible void __init xen_start_kernel(void)
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];

- local_irq_disable();
- early_boot_irqs_disabled = true;
+ if (!xen_hvm_domain()) {
+ if (!xen_pvh_domain()) {
+ pv_cpu_ops = xen_cpu_ops;

- xen_raw_console_write("mapping kernel into physical memory\n");
- xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
- xen_start_info->nr_pages);
- xen_reserve_special_pages();
+ x86_platform.get_nmi_reason = xen_get_nmi_reason;
+ }

- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
+ 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.oem.arch_setup = xen_arch_setup;
+ x86_init.oem.banner = xen_banner;

- /* keep using Xen gdt for now; no urgent need to change it */
+ /*
+ * Set up some pagetable state before starting to set any ptes.
+ */

-#ifdef CONFIG_X86_32
- pv_info.kernel_rpl = 1;
- if (xen_feature(XENFEAT_supervisor_mode_kernel))
- pv_info.kernel_rpl = 0;
-#else
- pv_info.kernel_rpl = 0;
-#endif
- /* set the limit of our address space */
- xen_reserve_top();
+ xen_init_mmu_ops();
+
+ /* Prevent unwanted bits from being set in PTEs. */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;

- /* 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.
+ * Prevent page tables from being allocated in highmem, even
+ * if CONFIG_HIGHPTE is enabled.
*/
- 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);
- }
+ __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+
+ /* Work out if we support NX */
+ x86_configure_nx();
+
+ /* Get mfn list */
+ xen_build_dynamic_phys_to_machine();
+
+ /*
+ * Set up kernel GDT and segment registers, mainly so that
+ * -fstack-protector code can be executed.
+ */
+ xen_setup_gdt(0);
+
+ if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
+ pv_mmu_ops.ptep_modify_prot_start =
+ xen_ptep_modify_prot_start;
+ pv_mmu_ops.ptep_modify_prot_commit =
+ xen_ptep_modify_prot_commit;
+ }
+
+ /*
+ * The only reliable way to retain the initial address of the
+ * percpu gdt_page is to remember it here, so we can go and
+ * mark it RW later, when the initial percpu area is freed.
+ */
+ xen_initial_gdt = &per_cpu(gdt_page, 0);
+
+ xen_raw_console_write("mapping kernel into physical memory\n");
+ xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
+ xen_start_info->nr_pages);
+ xen_reserve_special_pages();
+
+ /*
+ * Modify the cache mode translation tables to match Xen's PAT
+ * configuration.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ pat_init_cache_modes(pat);
+
+ /* keep using Xen gdt for now; no urgent need to change it */

#ifdef CONFIG_X86_32
- /* set up basic CPUID stuff */
- cpu_detect(&new_cpu_data);
- set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
- new_cpu_data.wp_works_ok = 1;
- new_cpu_data.x86_capability[0] = cpuid_edx(1);
+ pv_info.kernel_rpl = 1;
+ if (xen_feature(XENFEAT_supervisor_mode_kernel))
+ pv_info.kernel_rpl = 0;
+#else
+ pv_info.kernel_rpl = 0;
+#endif
+ /* 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);
+ }
+
+#ifdef CONFIG_X86_32
+ /* set up basic CPUID stuff */
+ cpu_detect(&new_cpu_data);
+ set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
+ new_cpu_data.wp_works_ok = 1;
+ new_cpu_data.x86_capability[0] = cpuid_edx(1);
#endif

- if (xen_start_info->mod_start) {
- if (xen_start_info->flags & SIF_MOD_START_PFN)
- initrd_start = PFN_PHYS(xen_start_info->mod_start);
- else
- initrd_start = __pa(xen_start_info->mod_start);
+ if (xen_start_info->mod_start) {
+ if (xen_start_info->flags & SIF_MOD_START_PFN)
+ initrd_start =
+ PFN_PHYS(xen_start_info->mod_start);
+ else
+ initrd_start = __pa(xen_start_info->mod_start);
+ }
+
+ /* Poke various useful things into boot_params */
+ boot_params.hdr.type_of_loader = (9 << 4) | 0;
+ boot_params.hdr.ramdisk_image = initrd_start;
+ boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
+ boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
}

- /* Poke various useful things into boot_params */
- boot_params.hdr.type_of_loader = (9 << 4) | 0;
- boot_params.hdr.ramdisk_image = initrd_start;
- boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
- boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+ local_irq_disable();
+ early_boot_irqs_disabled = true;

if (!xen_initial_domain()) {
add_preferred_console("xenboot", 0, NULL);
@@ -1713,6 +1716,16 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_setup_runstate_info(0);

xen_efi_init();
+}
+
+/* First C function to be called on Xen boot */
+asmlinkage __visible void __init xen_start_kernel(void)
+{
+ if (!xen_start_info)
+ return;
+ xen_domain_type = XEN_PV_DOMAIN;
+
+ xen_init_kernel();

/* Start the world */
#ifdef CONFIG_X86_32
--
1.7.1