Fixed MTP to work with TWRP

arch/x86/platform/efi/Makefile

@@ -0,0 +1,4 @@
+obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
+obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
+obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
+obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o

arch/x86/platform/efi/early_printk.c

@@ -0,0 +1,236 @@
+/*
+ * Copyright (C) 2013 Intel Corporation; author Matt Fleming
+ *
+ *  This file is part of the Linux kernel, and is made available under
+ *  the terms of the GNU General Public License version 2.
+ */
+
+#include <linux/console.h>
+#include <linux/efi.h>
+#include <linux/font.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <asm/setup.h>
+
+static const struct font_desc *font;
+static u32 efi_x, efi_y;
+static void *efi_fb;
+static bool early_efi_keep;
+
+/*
+ * efi earlyprintk need use early_ioremap to map the framebuffer.
+ * But early_ioremap is not usable for earlyprintk=efi,keep, ioremap should
+ * be used instead. ioremap will be available after paging_init() which is
+ * earlier than initcall callbacks. Thus adding this early initcall function
+ * early_efi_map_fb to map the whole efi framebuffer.
+ */
+static __init int early_efi_map_fb(void)
+{
+	unsigned long base, size;
+
+	if (!early_efi_keep)
+		return 0;
+
+	base = boot_params.screen_info.lfb_base;
+	size = boot_params.screen_info.lfb_size;
+	efi_fb = ioremap(base, size);
+
+	return efi_fb ? 0 : -ENOMEM;
+}
+early_initcall(early_efi_map_fb);
+
+/*
+ * early_efi_map maps efi framebuffer region [start, start + len -1]
+ * In case earlyprintk=efi,keep we have the whole framebuffer mapped already
+ * so just return the offset efi_fb + start.
+ */
+static __init_refok void *early_efi_map(unsigned long start, unsigned long len)
+{
+	unsigned long base;
+
+	base = boot_params.screen_info.lfb_base;
+
+	if (efi_fb)
+		return (efi_fb + start);
+	else
+		return early_ioremap(base + start, len);
+}
+
+static __init_refok void early_efi_unmap(void *addr, unsigned long len)
+{
+	if (!efi_fb)
+		early_iounmap(addr, len);
+}
+
+static void early_efi_clear_scanline(unsigned int y)
+{
+	unsigned long *dst;
+	u16 len;
+
+	len = boot_params.screen_info.lfb_linelength;
+	dst = early_efi_map(y*len, len);
+	if (!dst)
+		return;
+
+	memset(dst, 0, len);
+	early_efi_unmap(dst, len);
+}
+
+static void early_efi_scroll_up(void)
+{
+	unsigned long *dst, *src;
+	u16 len;
+	u32 i, height;
+
+	len = boot_params.screen_info.lfb_linelength;
+	height = boot_params.screen_info.lfb_height;
+
+	for (i = 0; i < height - font->height; i++) {
+		dst = early_efi_map(i*len, len);
+		if (!dst)
+			return;
+
+		src = early_efi_map((i + font->height) * len, len);
+		if (!src) {
+			early_efi_unmap(dst, len);
+			return;
+		}
+
+		memmove(dst, src, len);
+
+		early_efi_unmap(src, len);
+		early_efi_unmap(dst, len);
+	}
+}
+
+static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h)
+{
+	const u32 color_black = 0x00000000;
+	const u32 color_white = 0x00ffffff;
+	const u8 *src;
+	u8 s8;
+	int m;
+
+	src = font->data + c * font->height;
+	s8 = *(src + h);
+
+	for (m = 0; m < 8; m++) {
+		if ((s8 >> (7 - m)) & 1)
+			*dst = color_white;
+		else
+			*dst = color_black;
+		dst++;
+	}
+}
+
+static void
+early_efi_write(struct console *con, const char *str, unsigned int num)
+{
+	struct screen_info *si;
+	unsigned int len;
+	const char *s;
+	void *dst;
+
+	si = &boot_params.screen_info;
+	len = si->lfb_linelength;
+
+	while (num) {
+		unsigned int linemax;
+		unsigned int h, count = 0;
+
+		for (s = str; *s && *s != '\n'; s++) {
+			if (count == num)
+				break;
+			count++;
+		}
+
+		linemax = (si->lfb_width - efi_x) / font->width;
+		if (count > linemax)
+			count = linemax;
+
+		for (h = 0; h < font->height; h++) {
+			unsigned int n, x;
+
+			dst = early_efi_map((efi_y + h) * len, len);
+			if (!dst)
+				return;
+
+			s = str;
+			n = count;
+			x = efi_x;
+
+			while (n-- > 0) {
+				early_efi_write_char(dst + x*4, *s, h);
+				x += font->width;
+				s++;
+			}
+
+			early_efi_unmap(dst, len);
+		}
+
+		num -= count;
+		efi_x += count * font->width;
+		str += count;
+
+		if (num > 0 && *s == '\n') {
+			efi_x = 0;
+			efi_y += font->height;
+			str++;
+			num--;
+		}
+
+		if (efi_x >= si->lfb_width) {
+			efi_x = 0;
+			efi_y += font->height;
+		}
+
+		if (efi_y + font->height > si->lfb_height) {
+			u32 i;
+
+			efi_y -= font->height;
+			early_efi_scroll_up();
+
+			for (i = 0; i < font->height; i++)
+				early_efi_clear_scanline(efi_y + i);
+		}
+	}
+}
+
+static __init int early_efi_setup(struct console *con, char *options)
+{
+	struct screen_info *si;
+	u16 xres, yres;
+	u32 i;
+
+	si = &boot_params.screen_info;
+	xres = si->lfb_width;
+	yres = si->lfb_height;
+
+	/*
+	 * early_efi_write_char() implicitly assumes a framebuffer with
+	 * 32-bits per pixel.
+	 */
+	if (si->lfb_depth != 32)
+		return -ENODEV;
+
+	font = get_default_font(xres, yres, -1, -1);
+	if (!font)
+		return -ENODEV;
+
+	efi_y = rounddown(yres, font->height) - font->height;
+	for (i = 0; i < (yres - efi_y) / font->height; i++)
+		early_efi_scroll_up();
+
+	/* early_console_register will unset CON_BOOT in case ,keep */
+	if (!(con->flags & CON_BOOT))
+		early_efi_keep = true;
+	return 0;
+}
+
+struct console early_efi_console = {
+	.name =		"earlyefi",
+	.write =	early_efi_write,
+	.setup =	early_efi_setup,
+	.flags =	CON_PRINTBUFFER,
+	.index =	-1,
+};

arch/x86/platform/efi/efi-bgrt.c

@@ -0,0 +1,105 @@
+/*
+ * Copyright 2012 Intel Corporation
+ * Author: Josh Triplett <josh@joshtriplett.org>
+ *
+ * Based on the bgrt driver:
+ * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
+ * Author: Matthew Garrett
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/efi.h>
+#include <linux/efi-bgrt.h>
+
+struct acpi_table_bgrt *bgrt_tab;
+void *__initdata bgrt_image;
+size_t __initdata bgrt_image_size;
+
+struct bmp_header {
+	u16 id;
+	u32 size;
+} __packed;
+
+void __init efi_bgrt_init(void)
+{
+	acpi_status status;
+	void __iomem *image;
+	bool ioremapped = false;
+	struct bmp_header bmp_header;
+
+	if (acpi_disabled)
+		return;
+
+	status = acpi_get_table("BGRT", 0,
+	                        (struct acpi_table_header **)&bgrt_tab);
+	if (ACPI_FAILURE(status))
+		return;
+
+	if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+		pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n",
+		       bgrt_tab->header.length, sizeof(*bgrt_tab));
+		return;
+	}
+	if (bgrt_tab->version != 1) {
+		pr_err("Ignoring BGRT: invalid version %u (expected 1)\n",
+		       bgrt_tab->version);
+		return;
+	}
+	if (bgrt_tab->status != 1) {
+		pr_err("Ignoring BGRT: invalid status %u (expected 1)\n",
+		       bgrt_tab->status);
+		return;
+	}
+	if (bgrt_tab->image_type != 0) {
+		pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n",
+		       bgrt_tab->image_type);
+		return;
+	}
+	if (!bgrt_tab->image_address) {
+		pr_err("Ignoring BGRT: null image address\n");
+		return;
+	}
+
+	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
+	if (!image) {
+		image = early_memremap(bgrt_tab->image_address,
+				       sizeof(bmp_header));
+		ioremapped = true;
+		if (!image) {
+			pr_err("Ignoring BGRT: failed to map image header memory\n");
+			return;
+		}
+	}
+
+	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
+	if (ioremapped)
+		early_iounmap(image, sizeof(bmp_header));
+	bgrt_image_size = bmp_header.size;
+
+	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!bgrt_image) {
+		pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
+		       bgrt_image_size);
+		return;
+	}
+
+	if (ioremapped) {
+		image = early_memremap(bgrt_tab->image_address,
+				       bmp_header.size);
+		if (!image) {
+			pr_err("Ignoring BGRT: failed to map image memory\n");
+			kfree(bgrt_image);
+			bgrt_image = NULL;
+			return;
+		}
+	}
+
+	memcpy_fromio(bgrt_image, image, bgrt_image_size);
+	if (ioremapped)
+		early_iounmap(image, bmp_header.size);
+}

arch/x86/platform/efi/efi.c

@@ -0,0 +1,945 @@
+/*
+ * Common EFI (Extensible Firmware Interface) support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * 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) 2013 SuSE Labs
+ *	Borislav Petkov <bp@suse.de> - runtime services VA mapping
+ *
+ * Copied from efi_32.c to eliminate the duplicated code between EFI
+ * 32/64 support code. --ying 2007-10-26
+ *
+ * All EFI Runtime Services are not implemented yet as EFI only
+ * supports physical mode addressing on SoftSDV. This is to be fixed
+ * in a future version.  --drummond 1999-07-20
+ *
+ * Implemented EFI runtime services and virtual mode calls.  --davidm
+ *
+ * Goutham Rao: <goutham.rao@intel.com>
+ *	Skip non-WB memory and ignore empty memory ranges.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/efi.h>
+#include <linux/efi-bgrt.h>
+#include <linux/export.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/time.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <linux/bcd.h>
+
+#include <asm/setup.h>
+#include <asm/efi.h>
+#include <asm/time.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/x86_init.h>
+#include <asm/rtc.h>
+#include <asm/uv/uv.h>
+
+#define EFI_DEBUG
+
+struct efi_memory_map memmap;
+
+static struct efi efi_phys __initdata;
+static efi_system_table_t efi_systab __initdata;
+
+static efi_config_table_type_t arch_tables[] __initdata = {
+#ifdef CONFIG_X86_UV
+	{UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+	{NULL_GUID, NULL, NULL},
+};
+
+u64 efi_setup;		/* efi setup_data physical address */
+
+static int add_efi_memmap __initdata;
+static int __init setup_add_efi_memmap(char *arg)
+{
+	add_efi_memmap = 1;
+	return 0;
+}
+early_param("add_efi_memmap", setup_add_efi_memmap);
+
+static efi_status_t __init phys_efi_set_virtual_address_map(
+	unsigned long memory_map_size,
+	unsigned long descriptor_size,
+	u32 descriptor_version,
+	efi_memory_desc_t *virtual_map)
+{
+	efi_status_t status;
+
+	efi_call_phys_prolog();
+	status = efi_call_phys(efi_phys.set_virtual_address_map,
+			       memory_map_size, descriptor_size,
+			       descriptor_version, virtual_map);
+	efi_call_phys_epilog();
+	return status;
+}
+
+void efi_get_time(struct timespec *now)
+{
+	efi_status_t status;
+	efi_time_t eft;
+	efi_time_cap_t cap;
+
+	status = efi.get_time(&eft, &cap);
+	if (status != EFI_SUCCESS)
+		pr_err("Oops: efitime: can't read time!\n");
+
+	now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour,
+			     eft.minute, eft.second);
+	now->tv_nsec = 0;
+}
+
+/*
+ * Tell the kernel about the EFI memory map.  This might include
+ * more than the max 128 entries that can fit in the e820 legacy
+ * (zeropage) memory map.
+ */
+
+static void __init do_add_efi_memmap(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		int e820_type;
+
+		switch (md->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+			if (md->attribute & EFI_MEMORY_WB)
+				e820_type = E820_RAM;
+			else
+				e820_type = E820_RESERVED;
+			break;
+		case EFI_ACPI_RECLAIM_MEMORY:
+			e820_type = E820_ACPI;
+			break;
+		case EFI_ACPI_MEMORY_NVS:
+			e820_type = E820_NVS;
+			break;
+		case EFI_UNUSABLE_MEMORY:
+			e820_type = E820_UNUSABLE;
+			break;
+		default:
+			/*
+			 * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
+			 * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
+			 * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
+			 */
+			e820_type = E820_RESERVED;
+			break;
+		}
+		e820_add_region(start, size, e820_type);
+	}
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
+int __init efi_memblock_x86_reserve_range(void)
+{
+	struct efi_info *e = &boot_params.efi_info;
+	unsigned long pmap;
+
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+#ifdef CONFIG_X86_32
+	/* Can't handle data above 4GB at this time */
+	if (e->efi_memmap_hi) {
+		pr_err("Memory map is above 4GB, disabling EFI.\n");
+		return -EINVAL;
+	}
+	pmap =  e->efi_memmap;
+#else
+	pmap = (e->efi_memmap |	((__u64)e->efi_memmap_hi << 32));
+#endif
+	memmap.phys_map		= (void *)pmap;
+	memmap.nr_map		= e->efi_memmap_size /
+				  e->efi_memdesc_size;
+	memmap.desc_size	= e->efi_memdesc_size;
+	memmap.desc_version	= e->efi_memdesc_version;
+
+	memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
+
+	efi.memmap = &memmap;
+
+	return 0;
+}
+
+static void __init print_efi_memmap(void)
+{
+#ifdef EFI_DEBUG
+	efi_memory_desc_t *md;
+	void *p;
+	int i;
+
+	for (p = memmap.map, i = 0;
+	     p < memmap.map_end;
+	     p += memmap.desc_size, i++) {
+		char buf[64];
+
+		md = p;
+		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx) (%lluMB)\n",
+			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr,
+			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
+			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
+	}
+#endif  /*  EFI_DEBUG  */
+}
+
+void __init efi_unmap_memmap(void)
+{
+	clear_bit(EFI_MEMMAP, &efi.flags);
+	if (memmap.map) {
+		early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size);
+		memmap.map = NULL;
+	}
+}
+
+static int __init efi_systab_init(void *phys)
+{
+	if (efi_enabled(EFI_64BIT)) {
+		efi_system_table_64_t *systab64;
+		struct efi_setup_data *data = NULL;
+		u64 tmp = 0;
+
+		if (efi_setup) {
+			data = early_memremap(efi_setup, sizeof(*data));
+			if (!data)
+				return -ENOMEM;
+		}
+		systab64 = early_memremap((unsigned long)phys,
+					 sizeof(*systab64));
+		if (systab64 == NULL) {
+			pr_err("Couldn't map the system table!\n");
+			if (data)
+				early_memunmap(data, sizeof(*data));
+			return -ENOMEM;
+		}
+
+		efi_systab.hdr = systab64->hdr;
+		efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
+					      systab64->fw_vendor;
+		tmp |= data ? data->fw_vendor : systab64->fw_vendor;
+		efi_systab.fw_revision = systab64->fw_revision;
+		efi_systab.con_in_handle = systab64->con_in_handle;
+		tmp |= systab64->con_in_handle;
+		efi_systab.con_in = systab64->con_in;
+		tmp |= systab64->con_in;
+		efi_systab.con_out_handle = systab64->con_out_handle;
+		tmp |= systab64->con_out_handle;
+		efi_systab.con_out = systab64->con_out;
+		tmp |= systab64->con_out;
+		efi_systab.stderr_handle = systab64->stderr_handle;
+		tmp |= systab64->stderr_handle;
+		efi_systab.stderr = systab64->stderr;
+		tmp |= systab64->stderr;
+		efi_systab.runtime = data ?
+				     (void *)(unsigned long)data->runtime :
+				     (void *)(unsigned long)systab64->runtime;
+		tmp |= data ? data->runtime : systab64->runtime;
+		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
+		tmp |= systab64->boottime;
+		efi_systab.nr_tables = systab64->nr_tables;
+		efi_systab.tables = data ? (unsigned long)data->tables :
+					   systab64->tables;
+		tmp |= data ? data->tables : systab64->tables;
+
+		early_memunmap(systab64, sizeof(*systab64));
+		if (data)
+			early_memunmap(data, sizeof(*data));
+#ifdef CONFIG_X86_32
+		if (tmp >> 32) {
+			pr_err("EFI data located above 4GB, disabling EFI.\n");
+			return -EINVAL;
+		}
+#endif
+	} else {
+		efi_system_table_32_t *systab32;
+
+		systab32 = early_memremap((unsigned long)phys,
+					 sizeof(*systab32));
+		if (systab32 == NULL) {
+			pr_err("Couldn't map the system table!\n");
+			return -ENOMEM;
+		}
+
+		efi_systab.hdr = systab32->hdr;
+		efi_systab.fw_vendor = systab32->fw_vendor;
+		efi_systab.fw_revision = systab32->fw_revision;
+		efi_systab.con_in_handle = systab32->con_in_handle;
+		efi_systab.con_in = systab32->con_in;
+		efi_systab.con_out_handle = systab32->con_out_handle;
+		efi_systab.con_out = systab32->con_out;
+		efi_systab.stderr_handle = systab32->stderr_handle;
+		efi_systab.stderr = systab32->stderr;
+		efi_systab.runtime = (void *)(unsigned long)systab32->runtime;
+		efi_systab.boottime = (void *)(unsigned long)systab32->boottime;
+		efi_systab.nr_tables = systab32->nr_tables;
+		efi_systab.tables = systab32->tables;
+
+		early_memunmap(systab32, sizeof(*systab32));
+	}
+
+	efi.systab = &efi_systab;
+
+	/*
+	 * Verify the EFI Table
+	 */
+	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
+		pr_err("System table signature incorrect!\n");
+		return -EINVAL;
+	}
+	if ((efi.systab->hdr.revision >> 16) == 0)
+		pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n",
+		       efi.systab->hdr.revision >> 16,
+		       efi.systab->hdr.revision & 0xffff);
+
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+	return 0;
+}
+
+static int __init efi_runtime_init32(void)
+{
+	efi_runtime_services_32_t *runtime;
+
+	runtime = early_memremap((unsigned long)efi.systab->runtime,
+			sizeof(efi_runtime_services_32_t));
+	if (!runtime) {
+		pr_err("Could not map the runtime service table!\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * We will only need *early* access to the SetVirtualAddressMap
+	 * EFI runtime service. All other runtime services will be called
+	 * via the virtual mapping.
+	 */
+	efi_phys.set_virtual_address_map =
+			(efi_set_virtual_address_map_t *)
+			(unsigned long)runtime->set_virtual_address_map;
+	early_memunmap(runtime, sizeof(efi_runtime_services_32_t));
+
+	return 0;
+}
+
+static int __init efi_runtime_init64(void)
+{
+	efi_runtime_services_64_t *runtime;
+
+	runtime = early_memremap((unsigned long)efi.systab->runtime,
+			sizeof(efi_runtime_services_64_t));
+	if (!runtime) {
+		pr_err("Could not map the runtime service table!\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * We will only need *early* access to the SetVirtualAddressMap
+	 * EFI runtime service. All other runtime services will be called
+	 * via the virtual mapping.
+	 */
+	efi_phys.set_virtual_address_map =
+			(efi_set_virtual_address_map_t *)
+			(unsigned long)runtime->set_virtual_address_map;
+	early_memunmap(runtime, sizeof(efi_runtime_services_64_t));
+
+	return 0;
+}
+
+static int __init efi_runtime_init(void)
+{
+	int rv;
+
+	/*
+	 * Check out the runtime services table. We need to map
+	 * the runtime services table so that we can grab the physical
+	 * address of several of the EFI runtime functions, needed to
+	 * set the firmware into virtual mode.
+	 *
+	 * When EFI_PARAVIRT is in force then we could not map runtime
+	 * service memory region because we do not have direct access to it.
+	 * However, runtime services are available through proxy functions
+	 * (e.g. in case of Xen dom0 EFI implementation they call special
+	 * hypercall which executes relevant EFI functions) and that is why
+	 * they are always enabled.
+	 */
+
+	if (!efi_enabled(EFI_PARAVIRT)) {
+		if (efi_enabled(EFI_64BIT))
+			rv = efi_runtime_init64();
+		else
+			rv = efi_runtime_init32();
+
+		if (rv)
+			return rv;
+	}
+
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+	return 0;
+}
+
+static int __init efi_memmap_init(void)
+{
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+	/* Map the EFI memory map */
+	memmap.map = early_memremap((unsigned long)memmap.phys_map,
+				   memmap.nr_map * memmap.desc_size);
+	if (memmap.map == NULL) {
+		pr_err("Could not map the memory map!\n");
+		return -ENOMEM;
+	}
+	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+
+	if (add_efi_memmap)
+		do_add_efi_memmap();
+
+	set_bit(EFI_MEMMAP, &efi.flags);
+
+	return 0;
+}
+
+void __init efi_init(void)
+{
+	efi_char16_t *c16;
+	char vendor[100] = "unknown";
+	int i = 0;
+	void *tmp;
+
+#ifdef CONFIG_X86_32
+	if (boot_params.efi_info.efi_systab_hi ||
+	    boot_params.efi_info.efi_memmap_hi) {
+		pr_info("Table located above 4GB, disabling EFI.\n");
+		return;
+	}
+	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
+#else
+	efi_phys.systab = (efi_system_table_t *)
+			  (boot_params.efi_info.efi_systab |
+			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
+#endif
+
+	if (efi_systab_init(efi_phys.systab))
+		return;
+
+	efi.config_table = (unsigned long)efi.systab->tables;
+	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
+	efi.runtime	 = (unsigned long)efi.systab->runtime;
+
+	/*
+	 * Show what we know for posterity
+	 */
+	c16 = tmp = early_memremap(efi.systab->fw_vendor, 2);
+	if (c16) {
+		for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
+			vendor[i] = *c16++;
+		vendor[i] = '\0';
+	} else
+		pr_err("Could not map the firmware vendor!\n");
+	early_memunmap(tmp, 2);
+
+	pr_info("EFI v%u.%.02u by %s\n",
+		efi.systab->hdr.revision >> 16,
+		efi.systab->hdr.revision & 0xffff, vendor);
+
+	if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables))
+		return;
+
+	if (efi_config_init(arch_tables))
+		return;
+
+	/*
+	 * Note: We currently don't support runtime services on an EFI
+	 * that doesn't match the kernel 32/64-bit mode.
+	 */
+
+	if (!efi_runtime_supported())
+		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
+	else {
+		if (efi_runtime_disabled() || efi_runtime_init())
+			return;
+	}
+	if (efi_memmap_init())
+		return;
+
+	print_efi_memmap();
+}
+
+void __init efi_late_init(void)
+{
+	efi_bgrt_init();
+}
+
+void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
+{
+	u64 addr, npages;
+
+	addr = md->virt_addr;
+	npages = md->num_pages;
+
+	memrange_efi_to_native(&addr, &npages);
+
+	if (executable)
+		set_memory_x(addr, npages);
+	else
+		set_memory_nx(addr, npages);
+}
+
+void __init runtime_code_page_mkexec(void)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	/* Make EFI runtime service code area executable */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+
+		if (md->type != EFI_RUNTIME_SERVICES_CODE)
+			continue;
+
+		efi_set_executable(md, true);
+	}
+}
+
+void __init efi_memory_uc(u64 addr, unsigned long size)
+{
+	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
+	u64 npages;
+
+	npages = round_up(size, page_shift) / page_shift;
+	memrange_efi_to_native(&addr, &npages);
+	set_memory_uc(addr, npages);
+}
+
+void __init old_map_region(efi_memory_desc_t *md)
+{
+	u64 start_pfn, end_pfn, end;
+	unsigned long size;
+	void *va;
+
+	start_pfn = PFN_DOWN(md->phys_addr);
+	size	  = md->num_pages << PAGE_SHIFT;
+	end	  = md->phys_addr + size;
+	end_pfn   = PFN_UP(end);
+
+	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
+		va = __va(md->phys_addr);
+
+		if (!(md->attribute & EFI_MEMORY_WB))
+			efi_memory_uc((u64)(unsigned long)va, size);
+	} else
+		va = efi_ioremap(md->phys_addr, size,
+				 md->type, md->attribute);
+
+	md->virt_addr = (u64) (unsigned long) va;
+	if (!va)
+		pr_err("ioremap of 0x%llX failed!\n",
+		       (unsigned long long)md->phys_addr);
+}
+
+/* Merge contiguous regions of the same type and attribute */
+static void __init efi_merge_regions(void)
+{
+	void *p;
+	efi_memory_desc_t *md, *prev_md = NULL;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		u64 prev_size;
+		md = p;
+
+		if (!prev_md) {
+			prev_md = md;
+			continue;
+		}
+
+		if (prev_md->type != md->type ||
+		    prev_md->attribute != md->attribute) {
+			prev_md = md;
+			continue;
+		}
+
+		prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
+			prev_md->num_pages += md->num_pages;
+			md->type = EFI_RESERVED_TYPE;
+			md->attribute = 0;
+			continue;
+		}
+		prev_md = md;
+	}
+}
+
+static void __init get_systab_virt_addr(efi_memory_desc_t *md)
+{
+	unsigned long size;
+	u64 end, systab;
+
+	size = md->num_pages << EFI_PAGE_SHIFT;
+	end = md->phys_addr + size;
+	systab = (u64)(unsigned long)efi_phys.systab;
+	if (md->phys_addr <= systab && systab < end) {
+		systab += md->virt_addr - md->phys_addr;
+		efi.systab = (efi_system_table_t *)(unsigned long)systab;
+	}
+}
+
+static void __init save_runtime_map(void)
+{
+#ifdef CONFIG_KEXEC
+	efi_memory_desc_t *md;
+	void *tmp, *p, *q = NULL;
+	int count = 0;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
+		    (md->type == EFI_BOOT_SERVICES_CODE) ||
+		    (md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
+		if (!tmp)
+			goto out;
+		q = tmp;
+
+		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
+		count++;
+	}
+
+	efi_runtime_map_setup(q, count, memmap.desc_size);
+	return;
+
+out:
+	kfree(q);
+	pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+#endif
+}
+
+static void *realloc_pages(void *old_memmap, int old_shift)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+	if (!ret)
+		goto out;
+
+	/*
+	 * A first-time allocation doesn't have anything to copy.
+	 */
+	if (!old_memmap)
+		return ret;
+
+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+	free_pages((unsigned long)old_memmap, old_shift);
+	return ret;
+}
+
+/*
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
+ */
+static void * __init efi_map_regions(int *count, int *pg_shift)
+{
+	void *p, *new_memmap = NULL;
+	unsigned long left = 0;
+	efi_memory_desc_t *md;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+			if (md->type != EFI_BOOT_SERVICES_CODE &&
+			    md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+				continue;
+		}
+
+		efi_map_region(md);
+		get_systab_virt_addr(md);
+
+		if (left < memmap.desc_size) {
+			new_memmap = realloc_pages(new_memmap, *pg_shift);
+			if (!new_memmap)
+				return NULL;
+
+			left += PAGE_SIZE << *pg_shift;
+			(*pg_shift)++;
+		}
+
+		memcpy(new_memmap + (*count * memmap.desc_size), md,
+		       memmap.desc_size);
+
+		left -= memmap.desc_size;
+		(*count)++;
+	}
+
+	return new_memmap;
+}
+
+static void __init kexec_enter_virtual_mode(void)
+{
+#ifdef CONFIG_KEXEC
+	efi_memory_desc_t *md;
+	void *p;
+
+	efi.systab = NULL;
+
+	/*
+	 * We don't do virtual mode, since we don't do runtime services, on
+	 * non-native EFI
+	 */
+	if (!efi_is_native()) {
+		efi_unmap_memmap();
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	/*
+	* Map efi regions which were passed via setup_data. The virt_addr is a
+	* fixed addr which was used in first kernel of a kexec boot.
+	*/
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+		get_systab_virt_addr(md);
+	}
+
+	save_runtime_map();
+
+	BUG_ON(!efi.systab);
+
+	efi_sync_low_kernel_mappings();
+
+	/*
+	 * Now that EFI is in virtual mode, update the function
+	 * pointers in the runtime service table to the new virtual addresses.
+	 *
+	 * Call EFI services through wrapper functions.
+	 */
+	efi.runtime_version = efi_systab.hdr.revision;
+
+	efi_native_runtime_setup();
+
+	efi.set_virtual_address_map = NULL;
+
+	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
+		runtime_code_page_mkexec();
+
+	/* clean DUMMY object */
+	efi_delete_dummy_variable();
+#endif
+}
+
+/*
+ * This function will switch the EFI runtime services to virtual mode.
+ * Essentially, we look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor into the
+ * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ *
+ * The old method which used to update that memory descriptor with the
+ * virtual address obtained from ioremap() is still supported when the
+ * kernel is booted with efi=old_map on its command line. Same old
+ * method enabled the runtime services to be called without having to
+ * thunk back into physical mode for every invocation.
+ *
+ * The new method does a pagetable switch in a preemption-safe manner
+ * so that we're in a different address space when calling a runtime
+ * function. For function arguments passing we do copy the PGDs of the
+ * kernel page table into ->trampoline_pgd prior to each call.
+ *
+ * Specially for kexec boot, efi runtime maps in previous kernel should
+ * be passed in via setup_data. In that case runtime ranges will be mapped
+ * to the same virtual addresses as the first kernel, see
+ * kexec_enter_virtual_mode().
+ */
+static void __init __efi_enter_virtual_mode(void)
+{
+	int count = 0, pg_shift = 0;
+	void *new_memmap = NULL;
+	efi_status_t status;
+
+	efi.systab = NULL;
+
+	efi_merge_regions();
+	new_memmap = efi_map_regions(&count, &pg_shift);
+	if (!new_memmap) {
+		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	save_runtime_map();
+
+	BUG_ON(!efi.systab);
+
+	if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) {
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	efi_sync_low_kernel_mappings();
+	efi_dump_pagetable();
+
+	if (efi_is_native()) {
+		status = phys_efi_set_virtual_address_map(
+				memmap.desc_size * count,
+				memmap.desc_size,
+				memmap.desc_version,
+				(efi_memory_desc_t *)__pa(new_memmap));
+	} else {
+		status = efi_thunk_set_virtual_address_map(
+				efi_phys.set_virtual_address_map,
+				memmap.desc_size * count,
+				memmap.desc_size,
+				memmap.desc_version,
+				(efi_memory_desc_t *)__pa(new_memmap));
+	}
+
+	if (status != EFI_SUCCESS) {
+		pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+			 status);
+		panic("EFI call to SetVirtualAddressMap() failed!");
+	}
+
+	/*
+	 * Now that EFI is in virtual mode, update the function
+	 * pointers in the runtime service table to the new virtual addresses.
+	 *
+	 * Call EFI services through wrapper functions.
+	 */
+	efi.runtime_version = efi_systab.hdr.revision;
+
+	if (efi_is_native())
+		efi_native_runtime_setup();
+	else
+		efi_thunk_runtime_setup();
+
+	efi.set_virtual_address_map = NULL;
+
+	efi_runtime_mkexec();
+
+	/*
+	 * We mapped the descriptor array into the EFI pagetable above but we're
+	 * not unmapping it here. Here's why:
+	 *
+	 * We're copying select PGDs from the kernel page table to the EFI page
+	 * table and when we do so and make changes to those PGDs like unmapping
+	 * stuff from them, those changes appear in the kernel page table and we
+	 * go boom.
+	 *
+	 * From setup_real_mode():
+	 *
+	 * ...
+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+	 *
+	 * In this particular case, our allocation is in PGD 0 of the EFI page
+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
+	 *
+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+	 *
+	 * where the direct memory mapping in kernel space is.
+	 *
+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
+	 * it would get cleared in the kernel page table too.
+	 *
+	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
+	 */
+	free_pages((unsigned long)new_memmap, pg_shift);
+
+	/* clean DUMMY object */
+	efi_delete_dummy_variable();
+}
+
+void __init efi_enter_virtual_mode(void)
+{
+	if (efi_enabled(EFI_PARAVIRT))
+		return;
+
+	if (efi_setup)
+		kexec_enter_virtual_mode();
+	else
+		__efi_enter_virtual_mode();
+}
+
+/*
+ * Convenience functions to obtain memory types and attributes
+ */
+u32 efi_mem_type(unsigned long phys_addr)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if ((md->phys_addr <= phys_addr) &&
+		    (phys_addr < (md->phys_addr +
+				  (md->num_pages << EFI_PAGE_SHIFT))))
+			return md->type;
+	}
+	return 0;
+}
+
+u64 efi_mem_attributes(unsigned long phys_addr)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if ((md->phys_addr <= phys_addr) &&
+		    (phys_addr < (md->phys_addr +
+				  (md->num_pages << EFI_PAGE_SHIFT))))
+			return md->attribute;
+	}
+	return 0;
+}
+
+static int __init arch_parse_efi_cmdline(char *str)
+{
+	if (parse_option_str(str, "old_map"))
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+
+	return 0;
+}
+early_param("efi", arch_parse_efi_cmdline);

arch/x86/platform/efi/efi_32.c

@@ -0,0 +1,92 @@
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * 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>
+ *
+ * All EFI Runtime Services are not implemented yet as EFI only
+ * supports physical mode addressing on SoftSDV. This is to be fixed
+ * in a future version.  --drummond 1999-07-20
+ *
+ * Implemented EFI runtime services and virtual mode calls.  --davidm
+ *
+ * Goutham Rao: <goutham.rao@intel.com>
+ *	Skip non-WB memory and ignore empty memory ranges.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/efi.h>
+
+#include <asm/io.h>
+#include <asm/desc.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/efi.h>
+
+/*
+ * To make EFI call EFI runtime service in physical addressing mode we need
+ * prolog/epilog before/after the invocation to disable interrupt, to
+ * claim EFI runtime service handler exclusively and to duplicate a memory in
+ * low memory space say 0 - 3G.
+ */
+static unsigned long efi_rt_eflags;
+
+void efi_sync_low_kernel_mappings(void) {}
+void __init efi_dump_pagetable(void) {}
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	return 0;
+}
+void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	old_map_region(md);
+}
+
+void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
+
+void __init efi_call_phys_prolog(void)
+{
+	struct desc_ptr gdt_descr;
+
+	local_irq_save(efi_rt_eflags);
+
+	load_cr3(initial_page_table);
+	__flush_tlb_all();
+
+	gdt_descr.address = __pa(get_cpu_gdt_table(0));
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+
+void __init efi_call_phys_epilog(void)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+
+	load_cr3(swapper_pg_dir);
+	__flush_tlb_all();
+
+	local_irq_restore(efi_rt_eflags);
+}
+
+void __init efi_runtime_mkexec(void)
+{
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}

arch/x86/platform/efi/efi_64.c

@@ -0,0 +1,604 @@
+/*
+ * x86_64 specific EFI support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * 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>
+ *
+ * Code to convert EFI to E820 map has been implemented in elilo bootloader
+ * based on a EFI patch by Edgar Hucek. Based on the E820 map, the page table
+ * is setup appropriately for EFI runtime code.
+ * - mouli 06/14/2007.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bootmem.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/efi.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/e820.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/proto.h>
+#include <asm/efi.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/realmode.h>
+#include <asm/time.h>
+
+static pgd_t *save_pgd __initdata;
+static unsigned long efi_flags __initdata;
+
+/*
+ * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
+ */
+static u64 efi_va	= -4 * (1UL << 30);
+#define EFI_VA_END	(-68 * (1UL << 30))
+
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64 r15;
+	u64 prev_cr3;
+	pgd_t *efi_pgt;
+	bool use_pgd;
+	u64 phys_stack;
+} __packed;
+
+static void __init early_code_mapping_set_exec(int executable)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return;
+
+	/* Make EFI service code area executable */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+		    md->type == EFI_BOOT_SERVICES_CODE)
+			efi_set_executable(md, executable);
+	}
+}
+
+void __init efi_call_phys_prolog(void)
+{
+	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	early_code_mapping_set_exec(1);
+	local_irq_save(efi_flags);
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
+	__flush_tlb_all();
+}
+
+void __init efi_call_phys_epilog(void)
+{
+	/*
+	 * After the lock is released, the original page table is restored.
+	 */
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
+	__flush_tlb_all();
+	local_irq_restore(efi_flags);
+	early_code_mapping_set_exec(0);
+}
+
+/*
+ * Add low kernel mappings for passing arguments to EFI functions.
+ */
+void efi_sync_low_kernel_mappings(void)
+{
+	unsigned num_pgds;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+
+	memcpy(pgd + pgd_index(PAGE_OFFSET),
+		init_mm.pgd + pgd_index(PAGE_OFFSET),
+		sizeof(pgd_t) * num_pgds);
+}
+
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	unsigned long text;
+	struct page *page;
+	unsigned npages;
+	pgd_t *pgd;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd = __va(efi_scratch.efi_pgt);
+
+	/*
+	 * It can happen that the physical address of new_memmap lands in memory
+	 * which is not mapped in the EFI page table. Therefore we need to go
+	 * and ident-map those pages containing the map before calling
+	 * phys_efi_set_virtual_address_map().
+	 */
+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+		return 1;
+	}
+
+	efi_scratch.use_pgd = true;
+
+	/*
+	 * When making calls to the firmware everything needs to be 1:1
+	 * mapped and addressable with 32-bit pointers. Map the kernel
+	 * text and allocate a new stack because we can't rely on the
+	 * stack pointer being < 4GB.
+	 */
+	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+		return 0;
+
+	page = alloc_page(GFP_KERNEL|__GFP_DMA32);
+	if (!page)
+		panic("Unable to allocate EFI runtime stack < 4GB\n");
+
+	efi_scratch.phys_stack = virt_to_phys(page_address(page));
+	efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */
+
+	npages = (_end - _text) >> PAGE_SHIFT;
+	text = __pa(_text);
+
+	if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
+		pr_err("Failed to map kernel text 1:1\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
+}
+
+static void __init __map_region(efi_memory_desc_t *md, u64 va)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned long pf = 0;
+
+	if (!(md->attribute & EFI_MEMORY_WB))
+		pf |= _PAGE_PCD;
+
+	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, va);
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	unsigned long size = md->num_pages << PAGE_SHIFT;
+	u64 pa = md->phys_addr;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return old_map_region(md);
+
+	/*
+	 * Make sure the 1:1 mappings are present as a catch-all for b0rked
+	 * firmware which doesn't update all internal pointers after switching
+	 * to virtual mode and would otherwise crap on us.
+	 */
+	__map_region(md, md->phys_addr);
+
+	/*
+	 * Enforce the 1:1 mapping as the default virtual address when
+	 * booting in EFI mixed mode, because even though we may be
+	 * running a 64-bit kernel, the firmware may only be 32-bit.
+	 */
+	if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) {
+		md->virt_addr = md->phys_addr;
+		return;
+	}
+
+	efi_va -= size;
+
+	/* Is PA 2M-aligned? */
+	if (!(pa & (PMD_SIZE - 1))) {
+		efi_va &= PMD_MASK;
+	} else {
+		u64 pa_offset = pa & (PMD_SIZE - 1);
+		u64 prev_va = efi_va;
+
+		/* get us the same offset within this 2M page */
+		efi_va = (efi_va & PMD_MASK) + pa_offset;
+
+		if (efi_va > prev_va)
+			efi_va -= PMD_SIZE;
+	}
+
+	if (efi_va < EFI_VA_END) {
+		pr_warn(FW_WARN "VA address range overflow!\n");
+		return;
+	}
+
+	/* Do the VA map */
+	__map_region(md, efi_va);
+	md->virt_addr = efi_va;
+}
+
+/*
+ * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
+ * md->virt_addr is the original virtual address which had been mapped in kexec
+ * 1st kernel.
+ */
+void __init efi_map_region_fixed(efi_memory_desc_t *md)
+{
+	__map_region(md, md->virt_addr);
+}
+
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
+				 u32 type, u64 attribute)
+{
+	unsigned long last_map_pfn;
+
+	if (type == EFI_MEMORY_MAPPED_IO)
+		return ioremap(phys_addr, size);
+
+	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
+	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+		unsigned long top = last_map_pfn << PAGE_SHIFT;
+		efi_ioremap(top, size - (top - phys_addr), type, attribute);
+	}
+
+	if (!(attribute & EFI_MEMORY_WB))
+		efi_memory_uc((u64)(unsigned long)__va(phys_addr), size);
+
+	return (void __iomem *)__va(phys_addr);
+}
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+}
+
+void __init efi_runtime_mkexec(void)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		runtime_code_page_mkexec();
+}
+
+void __init efi_dump_pagetable(void)
+{
+#ifdef CONFIG_EFI_PGT_DUMP
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	ptdump_walk_pgd_level(NULL, pgd);
+#endif
+}
+
+#ifdef CONFIG_EFI_MIXED
+extern efi_status_t efi64_thunk(u32, ...);
+
+#define runtime_service32(func)						 \
+({									 \
+	u32 table = (u32)(unsigned long)efi.systab;			 \
+	u32 *rt, *___f;							 \
+									 \
+	rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime));	 \
+	___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \
+	*___f;								 \
+})
+
+/*
+ * Switch to the EFI page tables early so that we can access the 1:1
+ * runtime services mappings which are not mapped in any other page
+ * tables. This function must be called before runtime_service32().
+ *
+ * Also, disable interrupts because the IDT points to 64-bit handlers,
+ * which aren't going to function correctly when we switch to 32-bit.
+ */
+#define efi_thunk(f, ...)						\
+({									\
+	efi_status_t __s;						\
+	unsigned long flags;						\
+	u32 func;							\
+									\
+	efi_sync_low_kernel_mappings();					\
+	local_irq_save(flags);						\
+									\
+	efi_scratch.prev_cr3 = read_cr3();				\
+	write_cr3((unsigned long)efi_scratch.efi_pgt);			\
+	__flush_tlb_all();						\
+									\
+	func = runtime_service32(f);					\
+	__s = efi64_thunk(func, __VA_ARGS__);			\
+									\
+	write_cr3(efi_scratch.prev_cr3);				\
+	__flush_tlb_all();						\
+	local_irq_restore(flags);					\
+									\
+	__s;								\
+})
+
+efi_status_t efi_thunk_set_virtual_address_map(
+	void *phys_set_virtual_address_map,
+	unsigned long memory_map_size,
+	unsigned long descriptor_size,
+	u32 descriptor_version,
+	efi_memory_desc_t *virtual_map)
+{
+	efi_status_t status;
+	unsigned long flags;
+	u32 func;
+
+	efi_sync_low_kernel_mappings();
+	local_irq_save(flags);
+
+	efi_scratch.prev_cr3 = read_cr3();
+	write_cr3((unsigned long)efi_scratch.efi_pgt);
+	__flush_tlb_all();
+
+	func = (u32)(unsigned long)phys_set_virtual_address_map;
+	status = efi64_thunk(func, memory_map_size, descriptor_size,
+			     descriptor_version, virtual_map);
+
+	write_cr3(efi_scratch.prev_cr3);
+	__flush_tlb_all();
+	local_irq_restore(flags);
+
+	return status;
+}
+
+static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	efi_status_t status;
+	u32 phys_tm, phys_tc;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+	phys_tc = virt_to_phys(tc);
+
+	status = efi_thunk(get_time, phys_tm, phys_tc);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t efi_thunk_set_time(efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(set_time, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
+			  efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_enabled, phys_pending, phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_enabled = virt_to_phys(enabled);
+	phys_pending = virt_to_phys(pending);
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(get_wakeup_time, phys_enabled,
+			     phys_pending, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	efi_status_t status;
+	u32 phys_tm;
+
+	spin_lock(&rtc_lock);
+
+	phys_tm = virt_to_phys(tm);
+
+	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
+
+	spin_unlock(&rtc_lock);
+
+	return status;
+}
+
+
+static efi_status_t
+efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 *attr, unsigned long *data_size, void *data)
+{
+	efi_status_t status;
+	u32 phys_name, phys_vendor, phys_attr;
+	u32 phys_data_size, phys_data;
+
+	phys_data_size = virt_to_phys(data_size);
+	phys_vendor = virt_to_phys(vendor);
+	phys_name = virt_to_phys(name);
+	phys_attr = virt_to_phys(attr);
+	phys_data = virt_to_phys(data);
+
+	status = efi_thunk(get_variable, phys_name, phys_vendor,
+			   phys_attr, phys_data_size, phys_data);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 attr, unsigned long data_size, void *data)
+{
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+
+	phys_name = virt_to_phys(name);
+	phys_vendor = virt_to_phys(vendor);
+	phys_data = virt_to_phys(data);
+
+	/* If data_size is > sizeof(u32) we've got problems */
+	status = efi_thunk(set_variable, phys_name, phys_vendor,
+			   attr, data_size, phys_data);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_variable(unsigned long *name_size,
+			    efi_char16_t *name,
+			    efi_guid_t *vendor)
+{
+	efi_status_t status;
+	u32 phys_name_size, phys_name, phys_vendor;
+
+	phys_name_size = virt_to_phys(name_size);
+	phys_vendor = virt_to_phys(vendor);
+	phys_name = virt_to_phys(name);
+
+	status = efi_thunk(get_next_variable, phys_name_size,
+			   phys_name, phys_vendor);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_high_mono_count(u32 *count)
+{
+	efi_status_t status;
+	u32 phys_count;
+
+	phys_count = virt_to_phys(count);
+	status = efi_thunk(get_next_high_mono_count, phys_count);
+
+	return status;
+}
+
+static void
+efi_thunk_reset_system(int reset_type, efi_status_t status,
+		       unsigned long data_size, efi_char16_t *data)
+{
+	u32 phys_data;
+
+	phys_data = virt_to_phys(data);
+
+	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+}
+
+static efi_status_t
+efi_thunk_update_capsule(efi_capsule_header_t **capsules,
+			 unsigned long count, unsigned long sg_list)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
+			      u64 *remaining_space,
+			      u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	phys_storage = virt_to_phys(storage_space);
+	phys_remaining = virt_to_phys(remaining_space);
+	phys_max = virt_to_phys(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules,
+			     unsigned long count, u64 *max_size,
+			     int *reset_type)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+void efi_thunk_runtime_setup(void)
+{
+	efi.get_time = efi_thunk_get_time;
+	efi.set_time = efi_thunk_set_time;
+	efi.get_wakeup_time = efi_thunk_get_wakeup_time;
+	efi.set_wakeup_time = efi_thunk_set_wakeup_time;
+	efi.get_variable = efi_thunk_get_variable;
+	efi.get_next_variable = efi_thunk_get_next_variable;
+	efi.set_variable = efi_thunk_set_variable;
+	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
+	efi.reset_system = efi_thunk_reset_system;
+	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.update_capsule = efi_thunk_update_capsule;
+	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
+}
+#endif /* CONFIG_EFI_MIXED */

arch/x86/platform/efi/efi_stub_32.S

@@ -0,0 +1,123 @@
+/*
+ * EFI call stub for IA32.
+ *
+ * This stub allows us to make EFI calls in physical mode with interrupts
+ * turned off.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+/*
+ * efi_call_phys(void *, ...) is a function with variable parameters.
+ * All the callers of this function assure that all the parameters are 4-bytes.
+ */
+
+/*
+ * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save.
+ * So we'd better save all of them at the beginning of this function and restore
+ * at the end no matter how many we use, because we can not assure EFI runtime
+ * service functions will comply with gcc calling convention, too.
+ */
+
+.text
+ENTRY(efi_call_phys)
+	/*
+	 * 0. The function can only be called in Linux kernel. So CS has been
+	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
+	 * the values of these registers are the same. And, the corresponding
+	 * GDT entries are identical. So I will do nothing about segment reg
+	 * and GDT, but change GDT base register in prolog and epilog.
+	 */
+
+	/*
+	 * 1. Now I am running with EIP = <physical address> + PAGE_OFFSET.
+	 * But to make it smoothly switch from virtual mode to flat mode.
+	 * The mapping of lower virtual memory has been created in prolog and
+	 * epilog.
+	 */
+	movl	$1f, %edx
+	subl	$__PAGE_OFFSET, %edx
+	jmp	*%edx
+1:
+
+	/*
+	 * 2. Now on the top of stack is the return
+	 * address in the caller of efi_call_phys(), then parameter 1,
+	 * parameter 2, ..., param n. To make things easy, we save the return
+	 * address of efi_call_phys in a global variable.
+	 */
+	popl	%edx
+	movl	%edx, saved_return_addr
+	/* get the function pointer into ECX*/
+	popl	%ecx
+	movl	%ecx, efi_rt_function_ptr
+	movl	$2f, %edx
+	subl	$__PAGE_OFFSET, %edx
+	pushl	%edx
+
+	/*
+	 * 3. Clear PG bit in %CR0.
+	 */
+	movl	%cr0, %edx
+	andl	$0x7fffffff, %edx
+	movl	%edx, %cr0
+	jmp	1f
+1:
+
+	/*
+	 * 4. Adjust stack pointer.
+	 */
+	subl	$__PAGE_OFFSET, %esp
+
+	/*
+	 * 5. Call the physical function.
+	 */
+	jmp	*%ecx
+
+2:
+	/*
+	 * 6. After EFI runtime service returns, control will return to
+	 * following instruction. We'd better readjust stack pointer first.
+	 */
+	addl	$__PAGE_OFFSET, %esp
+
+	/*
+	 * 7. Restore PG bit
+	 */
+	movl	%cr0, %edx
+	orl	$0x80000000, %edx
+	movl	%edx, %cr0
+	jmp	1f
+1:
+	/*
+	 * 8. Now restore the virtual mode from flat mode by
+	 * adding EIP with PAGE_OFFSET.
+	 */
+	movl	$1f, %edx
+	jmp	*%edx
+1:
+
+	/*
+	 * 9. Balance the stack. And because EAX contain the return value,
+	 * we'd better not clobber it.
+	 */
+	leal	efi_rt_function_ptr, %edx
+	movl	(%edx), %ecx
+	pushl	%ecx
+
+	/*
+	 * 10. Push the saved return address onto the stack and return.
+	 */
+	leal	saved_return_addr, %edx
+	movl	(%edx), %ecx
+	pushl	%ecx
+	ret
+ENDPROC(efi_call_phys)
+.previous
+
+.data
+saved_return_addr:
+	.long 0
+efi_rt_function_ptr:
+	.long 0

arch/x86/platform/efi/efi_stub_64.S

@@ -0,0 +1,98 @@
+/*
+ * Function calling ABI conversion from Linux to EFI for x86_64
+ *
+ * Copyright (C) 2007 Intel Corp
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+#include <asm/page_types.h>
+
+#define SAVE_XMM			\
+	mov %rsp, %rax;			\
+	subq $0x70, %rsp;		\
+	and $~0xf, %rsp;		\
+	mov %rax, (%rsp);		\
+	mov %cr0, %rax;			\
+	clts;				\
+	mov %rax, 0x8(%rsp);		\
+	movaps %xmm0, 0x60(%rsp);	\
+	movaps %xmm1, 0x50(%rsp);	\
+	movaps %xmm2, 0x40(%rsp);	\
+	movaps %xmm3, 0x30(%rsp);	\
+	movaps %xmm4, 0x20(%rsp);	\
+	movaps %xmm5, 0x10(%rsp)
+
+#define RESTORE_XMM			\
+	movaps 0x60(%rsp), %xmm0;	\
+	movaps 0x50(%rsp), %xmm1;	\
+	movaps 0x40(%rsp), %xmm2;	\
+	movaps 0x30(%rsp), %xmm3;	\
+	movaps 0x20(%rsp), %xmm4;	\
+	movaps 0x10(%rsp), %xmm5;	\
+	mov 0x8(%rsp), %rsi;		\
+	mov %rsi, %cr0;			\
+	mov (%rsp), %rsp
+
+	/* stolen from gcc */
+	.macro FLUSH_TLB_ALL
+	movq %r15, efi_scratch(%rip)
+	movq %r14, efi_scratch+8(%rip)
+	movq %cr4, %r15
+	movq %r15, %r14
+	andb $0x7f, %r14b
+	movq %r14, %cr4
+	movq %r15, %cr4
+	movq efi_scratch+8(%rip), %r14
+	movq efi_scratch(%rip), %r15
+	.endm
+
+	.macro SWITCH_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 1f
+	movq %r15, efi_scratch(%rip)		# r15
+	# save previous CR3
+	movq %cr3, %r15
+	movq %r15, efi_scratch+8(%rip)		# prev_cr3
+	movq efi_scratch+16(%rip), %r15		# EFI pgt
+	movq %r15, %cr3
+	1:
+	.endm
+
+	.macro RESTORE_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 2f
+	movq efi_scratch+8(%rip), %r15
+	movq %r15, %cr3
+	movq efi_scratch(%rip), %r15
+	FLUSH_TLB_ALL
+	2:
+	.endm
+
+ENTRY(efi_call)
+	SAVE_XMM
+	mov (%rsp), %rax
+	mov 8(%rax), %rax
+	subq $48, %rsp
+	mov %r9, 32(%rsp)
+	mov %rax, 40(%rsp)
+	mov %r8, %r9
+	mov %rcx, %r8
+	mov %rsi, %rcx
+	SWITCH_PGT
+	call *%rdi
+	RESTORE_PGT
+	addq $48, %rsp
+	RESTORE_XMM
+	ret
+ENDPROC(efi_call)
+
+	.data
+ENTRY(efi_scratch)
+	.fill 3,8,0
+	.byte 0
+	.quad 0

arch/x86/platform/efi/efi_thunk_64.S

@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+#include <asm/segment.h>
+
+	.text
+	.code64
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	/*
+	 * Switch to 1:1 mapped 32-bit stack pointer.
+	 */
+	movq	%rsp, efi_saved_sp(%rip)
+	movq	efi_scratch+25(%rip), %rsp
+
+	/*
+	 * Calculate the physical address of the kernel text.
+	 */
+	movq	$__START_KERNEL_map, %rax
+	subq	phys_base(%rip), %rax
+
+	/*
+	 * Push some physical addresses onto the stack. This is easier
+	 * to do now in a code64 section while the assembler can address
+	 * 64-bit values. Note that all the addresses on the stack are
+	 * 32-bit.
+	 */
+	subq	$16, %rsp
+	leaq	efi_exit32(%rip), %rbx
+	subq	%rax, %rbx
+	movl	%ebx, 8(%rsp)
+
+	leaq	__efi64_thunk(%rip), %rbx
+	subq	%rax, %rbx
+	call	*%rbx
+
+	movq	efi_saved_sp(%rip), %rsp
+	pop	%rbx
+	pop	%rbp
+	retq
+ENDPROC(efi64_thunk)
+
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/* Switch to 32-bit descriptor */
+	pushq	$__KERNEL32_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
+
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	movl	72(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+func_rt_ptr:		.quad 0
+efi_saved_sp:		.quad 0

arch/x86/platform/efi/quirks.c

@@ -0,0 +1,290 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/acpi.h>
+#include <asm/efi.h>
+#include <asm/uv/uv.h>
+
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
+
+static bool efi_no_storage_paranoia;
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient
+ * space in the variable store. The implementation of garbage collection
+ * in some FW versions causes stale (deleted) variables to take up space
+ * longer than intended and space is only freed once the store becomes
+ * almost completely full.
+ *
+ * Enabling this option disables the space checks in
+ * efi_query_variable_store() and forces garbage collection.
+ *
+ * Only enable this option if deleting EFI variables does not free up
+ * space in your variable store, e.g. if despite deleting variables
+ * you're unable to create new ones.
+ */
+static int __init setup_storage_paranoia(char *arg)
+{
+	efi_no_storage_paranoia = true;
+	return 0;
+}
+early_param("efi_no_storage_paranoia", setup_storage_paranoia);
+
+/*
+ * Deleting the dummy variable which kicks off garbage collection
+*/
+void efi_delete_dummy_variable(void)
+{
+	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
+}
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient space
+ * in the variable store. Ensure that we never use more than a safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
+	status = efi.query_variable_info(attributes, &storage_size,
+					 &remaining_size, &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	/*
+	 * We account for that by refusing the write if permitting it would
+	 * reduce the available space to under 5KB. This figure was provided by
+	 * Samsung, so should be safe.
+	 */
+	if ((remaining_size - size < EFI_MIN_RESERVE) &&
+		!efi_no_storage_paranoia) {
+
+		/*
+		 * Triggering garbage collection may require that the firmware
+		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
+		 * that by attempting to use more space than is available.
+		 */
+		unsigned long dummy_size = remaining_size + 1024;
+		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
+
+		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					  EFI_VARIABLE_NON_VOLATILE |
+					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					  EFI_VARIABLE_RUNTIME_ACCESS,
+					  dummy_size, dummy);
+
+		if (status == EFI_SUCCESS) {
+			/*
+			 * This should have failed, so if it didn't make sure
+			 * that we delete it...
+			 */
+			efi_delete_dummy_variable();
+		}
+
+		kfree(dummy);
+
+		/*
+		 * The runtime code may now have triggered a garbage collection
+		 * run, so check the variable info again
+		 */
+		status = efi.query_variable_info(attributes, &storage_size,
+						 &remaining_size, &max_size);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		/*
+		 * There still isn't enough room, so return an error
+		 */
+		if (remaining_size - size < EFI_MIN_RESERVE)
+			return EFI_OUT_OF_RESOURCES;
+	}
+
+	return EFI_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(efi_query_variable_store);
+
+/*
+ * The UEFI specification makes it clear that the operating system is free to do
+ * whatever it wants with boot services code after ExitBootServices() has been
+ * called. Ignoring this recommendation a significant bunch of EFI implementations 
+ * continue calling into boot services code (SetVirtualAddressMap). In order to 
+ * work around such buggy implementations we reserve boot services region during 
+ * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it
+* is discarded.
+*/
+void __init efi_reserve_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start + size > __pa_symbol(_text)
+				&& start <= __pa_symbol(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_is_region_reserved(start, size)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
+				     start, start+size-1);
+		} else
+			memblock_reserve(start, size);
+	}
+}
+
+void __init efi_free_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
+		free_bootmem_late(start, size);
+	}
+
+	efi_unmap_memmap();
+}
+
+/*
+ * A number of config table entries get remapped to virtual addresses
+ * after entering EFI virtual mode. However, the kexec kernel requires
+ * their physical addresses therefore we pass them via setup_data and
+ * correct those entries to their respective physical addresses here.
+ *
+ * Currently only handles smbios which is necessary for some firmware
+ * implementation.
+ */
+int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	if (!efi_setup)
+		return 0;
+
+	if (!efi_enabled(EFI_64BIT))
+		return 0;
+
+	data = early_memremap(efi_setup, sizeof(*data));
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->smbios)
+		goto out_memremap;
+
+	sz = sizeof(efi_config_table_64_t);
+
+	p = tablep = early_memremap(tables, nr_tables * sz);
+	if (!p) {
+		pr_err("Could not map Configuration table!\n");
+		ret = -ENOMEM;
+		goto out_memremap;
+	}
+
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+
+		guid = ((efi_config_table_64_t *)p)->guid;
+
+		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = data->smbios;
+		p += sz;
+	}
+	early_memunmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_memunmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_runtime_supported()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+}
+
+/*
+ * For most modern platforms the preferred method of powering off is via
+ * ACPI. However, there are some that are known to require the use of
+ * EFI runtime services and for which ACPI does not work at all.
+ *
+ * Using EFI is a last resort, to be used only if no other option
+ * exists.
+ */
+bool efi_reboot_required(void)
+{
+	if (!acpi_gbl_reduced_hardware)
+		return false;
+
+	efi_reboot_quirk_mode = EFI_RESET_WARM;
+	return true;
+}
+
+bool efi_poweroff_required(void)
+{
+	return !!acpi_gbl_reduced_hardware;
+}