xen: Put EFI machinery in place

This patch enables EFI usage under Xen dom0. Standard EFI Linux
Kernel infrastructure cannot be used because it requires direct
access to EFI data and code. However, in dom0 case it is not possible
because above mentioned EFI stuff is fully owned and controlled
by Xen hypervisor. In this case all calls from dom0 to EFI must
be requested via special hypercall which in turn executes relevant
EFI code in behalf of dom0.

When dom0 kernel boots it checks for EFI availability on a machine.
If it is detected then artificial EFI system table is filled.
Native EFI callas are replaced by functions which mimics them
by calling relevant hypercall. Later pointer to EFI system table
is passed to standard EFI machinery and it continues EFI subsystem
initialization taking into account that there is no direct access
to EFI boot services, runtime, tables, structures, etc. After that
system runs as usual.

This patch is based on Jan Beulich and Tang Liang work.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Tang Liang <liang.tang@oracle.com>
Signed-off-by: Daniel Kiper <daniel.kiper@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

arch/x86/xen/enlighten.c

@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/edd.h>
+#include <linux/efi.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -1520,6 +1521,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	int rc;
+	efi_system_table_t *efi_systab_xen;
 
 	if (!xen_start_info)
 		return;
@@ -1715,6 +1717,19 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	xen_setup_runstate_info(0);
 
+	efi_systab_xen = xen_efi_probe();
+
+	if (efi_systab_xen) {
+		strncpy((char *)&boot_params.efi_info.efi_loader_signature, "Xen",
+				sizeof(boot_params.efi_info.efi_loader_signature));
+		boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
+		boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
+
+		set_bit(EFI_BOOT, &efi.flags);
+		set_bit(EFI_PARAVIRT, &efi.flags);
+		set_bit(EFI_64BIT, &efi.flags);
+	}
+
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();

drivers/xen/Kconfig

@@ -240,4 +240,8 @@ config XEN_MCE_LOG
 config XEN_HAVE_PVMMU
        bool
 
+config XEN_EFI
+	def_bool y
+	depends on X86_64 && EFI
+
 endmenu

drivers/xen/Makefile

@@ -9,6 +9,8 @@ obj-y	+= xenbus/
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_features.o			:= $(nostackp)
 
+CFLAGS_efi.o				+= -fshort-wchar
+
 dom0-$(CONFIG_PCI) += pci.o
 dom0-$(CONFIG_USB_SUPPORT) += dbgp.o
 dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y)
@@ -33,6 +35,7 @@ obj-$(CONFIG_XEN_STUB)			+= xen-stub.o
 obj-$(CONFIG_XEN_ACPI_HOTPLUG_MEMORY)	+= xen-acpi-memhotplug.o
 obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU)	+= xen-acpi-cpuhotplug.o
 obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o
+obj-$(CONFIG_XEN_EFI)			+= efi.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o

drivers/xen/efi.c

@@ -0,0 +1,368 @@
+/*
+ * EFI support for Xen.
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *	Stephane Eranian <eranian@hpl.hp.com>
+ * Copyright (C) 2005-2008 Intel Co.
+ *	Fenghua Yu <fenghua.yu@intel.com>
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Chandramouli Narayanan <mouli@linux.intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2011 Novell Co.
+ *	Jan Beulich <JBeulich@suse.com>
+ * Copyright (C) 2011-2012 Oracle Co.
+ *	Liang Tang <liang.tang@oracle.com>
+ * Copyright (c) 2014 Oracle Co., Daniel Kiper
+ */
+
+#include <linux/bug.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/string.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/platform.h>
+#include <xen/xen.h>
+
+#include <asm/xen/hypercall.h>
+
+#define INIT_EFI_OP(name) \
+	{.cmd = XENPF_efi_runtime_call, \
+	 .u.efi_runtime_call.function = XEN_EFI_##name, \
+	 .u.efi_runtime_call.misc = 0}
+
+#define efi_data(op)	(op.u.efi_runtime_call)
+
+static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_time);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	if (tm) {
+		BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_time.time));
+		memcpy(tm, &efi_data(op).u.get_time.time, sizeof(*tm));
+	}
+
+	if (tc) {
+		tc->resolution = efi_data(op).u.get_time.resolution;
+		tc->accuracy = efi_data(op).u.get_time.accuracy;
+		tc->sets_to_zero = !!(efi_data(op).misc &
+				      XEN_EFI_GET_TIME_SET_CLEARS_NS);
+	}
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_time(efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_time);
+
+	BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_time));
+	memcpy(&efi_data(op).u.set_time, tm, sizeof(*tm));
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled,
+					    efi_bool_t *pending,
+					    efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	if (tm) {
+		BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_wakeup_time));
+		memcpy(tm, &efi_data(op).u.get_wakeup_time, sizeof(*tm));
+	}
+
+	if (enabled)
+		*enabled = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_ENABLED);
+
+	if (pending)
+		*pending = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_PENDING);
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time);
+
+	BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_wakeup_time));
+	if (enabled)
+		efi_data(op).misc = XEN_EFI_SET_WAKEUP_TIME_ENABLE;
+	if (tm)
+		memcpy(&efi_data(op).u.set_wakeup_time, tm, sizeof(*tm));
+	else
+		efi_data(op).misc |= XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_variable(efi_char16_t *name,
+					 efi_guid_t *vendor,
+					 u32 *attr,
+					 unsigned long *data_size,
+					 void *data)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_variable);
+
+	set_xen_guest_handle(efi_data(op).u.get_variable.name, name);
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.get_variable.vendor_guid));
+	memcpy(&efi_data(op).u.get_variable.vendor_guid, vendor, sizeof(*vendor));
+	efi_data(op).u.get_variable.size = *data_size;
+	set_xen_guest_handle(efi_data(op).u.get_variable.data, data);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*data_size = efi_data(op).u.get_variable.size;
+	if (attr)
+		*attr = efi_data(op).misc;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
+					      efi_char16_t *name,
+					      efi_guid_t *vendor)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name);
+
+	efi_data(op).u.get_next_variable_name.size = *name_size;
+	set_xen_guest_handle(efi_data(op).u.get_next_variable_name.name, name);
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.get_next_variable_name.vendor_guid));
+	memcpy(&efi_data(op).u.get_next_variable_name.vendor_guid, vendor,
+	       sizeof(*vendor));
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*name_size = efi_data(op).u.get_next_variable_name.size;
+	memcpy(vendor, &efi_data(op).u.get_next_variable_name.vendor_guid,
+	       sizeof(*vendor));
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_variable(efi_char16_t *name,
+					 efi_guid_t *vendor,
+					 u32 attr,
+					 unsigned long data_size,
+					 void *data)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_variable);
+
+	set_xen_guest_handle(efi_data(op).u.set_variable.name, name);
+	efi_data(op).misc = attr;
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.set_variable.vendor_guid));
+	memcpy(&efi_data(op).u.set_variable.vendor_guid, vendor, sizeof(*vendor));
+	efi_data(op).u.set_variable.size = data_size;
+	set_xen_guest_handle(efi_data(op).u.set_variable.data, data);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_query_variable_info(u32 attr,
+						u64 *storage_space,
+						u64 *remaining_space,
+						u64 *max_variable_size)
+{
+	struct xen_platform_op op = INIT_EFI_OP(query_variable_info);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	efi_data(op).u.query_variable_info.attr = attr;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*storage_space = efi_data(op).u.query_variable_info.max_store_size;
+	*remaining_space = efi_data(op).u.query_variable_info.remain_store_size;
+	*max_variable_size = efi_data(op).u.query_variable_info.max_size;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*count = efi_data(op).misc;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
+					   unsigned long count,
+					   unsigned long sg_list)
+{
+	struct xen_platform_op op = INIT_EFI_OP(update_capsule);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	set_xen_guest_handle(efi_data(op).u.update_capsule.capsule_header_array,
+			     capsules);
+	efi_data(op).u.update_capsule.capsule_count = count;
+	efi_data(op).u.update_capsule.sg_list = sg_list;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+					       unsigned long count,
+					       u64 *max_size,
+					       int *reset_type)
+{
+	struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	set_xen_guest_handle(efi_data(op).u.query_capsule_capabilities.capsule_header_array,
+					capsules);
+	efi_data(op).u.query_capsule_capabilities.capsule_count = count;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*max_size = efi_data(op).u.query_capsule_capabilities.max_capsule_size;
+	*reset_type = efi_data(op).u.query_capsule_capabilities.reset_type;
+
+	return efi_data(op).status;
+}
+
+static efi_char16_t vendor[100] __initdata;
+
+static efi_system_table_t efi_systab_xen __initdata = {
+	.hdr = {
+		.signature	= EFI_SYSTEM_TABLE_SIGNATURE,
+		.revision	= 0, /* Initialized later. */
+		.headersize	= 0, /* Ignored by Linux Kernel. */
+		.crc32		= 0, /* Ignored by Linux Kernel. */
+		.reserved	= 0
+	},
+	.fw_vendor	= EFI_INVALID_TABLE_ADDR, /* Initialized later. */
+	.fw_revision	= 0,			  /* Initialized later. */
+	.con_in_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_in		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_out_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_out	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.stderr_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.stderr		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.runtime	= (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR,
+						  /* Not used under Xen. */
+	.boottime	= (efi_boot_services_t *)EFI_INVALID_TABLE_ADDR,
+						  /* Not used under Xen. */
+	.nr_tables	= 0,			  /* Initialized later. */
+	.tables		= EFI_INVALID_TABLE_ADDR  /* Initialized later. */
+};
+
+static const struct efi efi_xen __initconst = {
+	.systab                   = NULL, /* Initialized later. */
+	.runtime_version	  = 0,    /* Initialized later. */
+	.mps                      = EFI_INVALID_TABLE_ADDR,
+	.acpi                     = EFI_INVALID_TABLE_ADDR,
+	.acpi20                   = EFI_INVALID_TABLE_ADDR,
+	.smbios                   = EFI_INVALID_TABLE_ADDR,
+	.sal_systab               = EFI_INVALID_TABLE_ADDR,
+	.boot_info                = EFI_INVALID_TABLE_ADDR,
+	.hcdp                     = EFI_INVALID_TABLE_ADDR,
+	.uga                      = EFI_INVALID_TABLE_ADDR,
+	.uv_systab                = EFI_INVALID_TABLE_ADDR,
+	.fw_vendor                = EFI_INVALID_TABLE_ADDR,
+	.runtime                  = EFI_INVALID_TABLE_ADDR,
+	.config_table             = EFI_INVALID_TABLE_ADDR,
+	.get_time                 = xen_efi_get_time,
+	.set_time                 = xen_efi_set_time,
+	.get_wakeup_time          = xen_efi_get_wakeup_time,
+	.set_wakeup_time          = xen_efi_set_wakeup_time,
+	.get_variable             = xen_efi_get_variable,
+	.get_next_variable        = xen_efi_get_next_variable,
+	.set_variable             = xen_efi_set_variable,
+	.query_variable_info      = xen_efi_query_variable_info,
+	.update_capsule           = xen_efi_update_capsule,
+	.query_capsule_caps       = xen_efi_query_capsule_caps,
+	.get_next_high_mono_count = xen_efi_get_next_high_mono_count,
+	.reset_system             = NULL, /* Functionality provided by Xen. */
+	.set_virtual_address_map  = NULL, /* Not used under Xen. */
+	.memmap                   = NULL, /* Not used under Xen. */
+	.flags			  = 0     /* Initialized later. */
+};
+
+efi_system_table_t __init *xen_efi_probe(void)
+{
+	struct xen_platform_op op = {
+		.cmd = XENPF_firmware_info,
+		.u.firmware_info = {
+			.type = XEN_FW_EFI_INFO,
+			.index = XEN_FW_EFI_CONFIG_TABLE
+		}
+	};
+	union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
+
+	if (!xen_initial_domain() || HYPERVISOR_dom0_op(&op) < 0)
+		return NULL;
+
+	/* Here we know that Xen runs on EFI platform. */
+
+	efi = efi_xen;
+
+	efi_systab_xen.tables = info->cfg.addr;
+	efi_systab_xen.nr_tables = info->cfg.nent;
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_VENDOR;
+	info->vendor.bufsz = sizeof(vendor);
+	set_xen_guest_handle(info->vendor.name, vendor);
+
+	if (HYPERVISOR_dom0_op(&op) == 0) {
+		efi_systab_xen.fw_vendor = __pa_symbol(vendor);
+		efi_systab_xen.fw_revision = info->vendor.revision;
+	} else
+		efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN");
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_VERSION;
+
+	if (HYPERVISOR_dom0_op(&op) == 0)
+		efi_systab_xen.hdr.revision = info->version;
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
+
+	if (HYPERVISOR_dom0_op(&op) == 0)
+		efi.runtime_version = info->version;
+
+	return &efi_systab_xen;
+}

include/xen/xen-ops.h

@@ -3,6 +3,7 @@
 
 #include <linux/percpu.h>
 #include <linux/notifier.h>
+#include <linux/efi.h>
 #include <asm/xen/interface.h>
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
@@ -35,4 +36,14 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 			       int numpgs, struct page **pages);
 
 bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
+
+#ifdef CONFIG_XEN_EFI
+extern efi_system_table_t *xen_efi_probe(void);
+#else
+static efi_system_table_t __init *xen_efi_probe(void)
+{
+	return NULL;
+}
+#endif
+
 #endif /* INCLUDE_XEN_OPS_H */