x86, efi: EFI boot stub support

There is currently a large divide between kernel development and the
development of EFI boot loaders. The idea behind this patch is to give
the kernel developers full control over the EFI boot process. As
H. Peter Anvin put it,

"The 'kernel carries its own stub' approach been very successful in
dealing with BIOS, and would make a lot of sense to me for EFI as
well."

This patch introduces an EFI boot stub that allows an x86 bzImage to
be loaded and executed by EFI firmware. The bzImage appears to the
firmware as an EFI application. Luckily there are enough free bits
within the bzImage header so that it can masquerade as an EFI
application, thereby coercing the EFI firmware into loading it and
jumping to its entry point. The beauty of this masquerading approach
is that both BIOS and EFI boot loaders can still load and run the same
bzImage, thereby allowing a single kernel image to work in any boot
environment.

The EFI boot stub supports multiple initrds, but they must exist on
the same partition as the bzImage. Command-line arguments for the
kernel can be appended after the bzImage name when run from the EFI
shell, e.g.

Shell> bzImage console=ttyS0 root=/dev/sdb initrd=initrd.img

v7:
 - Fix checkpatch warnings.

v6:

 - Try to allocate initrd memory just below hdr->inird_addr_max.

v5:

 - load_options_size is UTF-16, which needs dividing by 2 to convert
   to the corresponding ASCII size.

v4:

 - Don't read more than image->load_options_size

v3:

 - Fix following warnings when compiling CONFIG_EFI_STUB=n

   arch/x86/boot/tools/build.c: In function ‘main’:
   arch/x86/boot/tools/build.c:138:24: warning: unused variable ‘pe_header’
   arch/x86/boot/tools/build.c:138:15: warning: unused variable ‘file_sz’

 - As reported by Matthew Garrett, some Apple machines have GOPs that
   don't have hardware attached. We need to weed these out by
   searching for ones that handle the PCIIO protocol.

 - Don't allocate memory if no initrds are on cmdline
 - Don't trust image->load_options_size

Maarten Lankhorst noted:
 - Don't strip first argument when booted from efibootmgr
 - Don't allocate too much memory for cmdline
 - Don't update cmdline_size, the kernel considers it read-only
 - Don't accept '\n' for initrd names

v2:

 - File alignment was too large, was 8192 should be 512. Reported by
   Maarten Lankhorst on LKML.
 - Added UGA support for graphics
 - Use VIDEO_TYPE_EFI instead of hard-coded number.
 - Move linelength assignment until after we've assigned depth
 - Dynamically fill out AddressOfEntryPoint in tools/build.c
 - Don't use magic number for GDT/TSS stuff. Requested by Andi Kleen
 - The bzImage may need to be relocated as it may have been loaded at
   a high address address by the firmware. This was required to get my
   macbook booting because the firmware loaded it at 0x7cxxxxxx, which
   triggers this error in decompress_kernel(),

	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
		error("Destination address too large");

Cc: Mike Waychison <mikew@google.com>
Cc: Matthew Garrett <mjg@redhat.com>
Tested-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Link: http://lkml.kernel.org/r/1321383097.2657.9.camel@mfleming-mobl1.ger.corp.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

8 files changed, 1221 insertions, 1 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 09664ef..b123b9a 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -23,7 +23,15 @@ LDFLAGS_vmlinux := -T
 
 hostprogs-y	:= mkpiggy
 
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE
+VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
+	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
+	$(obj)/piggy.o
+
+ifeq ($(CONFIG_EFI_STUB), y)
+	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+endif
+
+$(obj)/vmlinux: $(VMLINUX_OBJS) FORCE
 	$(call if_changed,ld)
 	@:
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
new file mode 100644
index 0000000..4055e63
--- /dev/null
+++ b/arch/x86/boot/compressed/eboot.c
@@ -0,0 +1,1014 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2011 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/efi.h>
+#include <asm/efi.h>
+#include <asm/setup.h>
+#include <asm/desc.h>
+
+#include "eboot.h"
+
+static efi_system_table_t *sys_table;
+
+static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size,
+			      unsigned long *desc_size)
+{
+	efi_memory_desc_t *m = NULL;
+	efi_status_t status;
+	unsigned long key;
+	u32 desc_version;
+
+	*map_size = sizeof(*m) * 32;
+again:
+	/*
+	 * Add an additional efi_memory_desc_t because we're doing an
+	 * allocation which may be in a new descriptor region.
+	 */
+	*map_size += sizeof(*m);
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, *map_size, (void **)&m);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	status = efi_call_phys5(sys_table->boottime->get_memory_map, map_size,
+				m, &key, desc_size, &desc_version);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		efi_call_phys1(sys_table->boottime->free_pool, m);
+		goto again;
+	}
+
+	if (status != EFI_SUCCESS)
+		efi_call_phys1(sys_table->boottime->free_pool, m);
+
+fail:
+	*map = m;
+	return status;
+}
+
+/*
+ * Allocate at the highest possible address that is not above 'max'.
+ */
+static efi_status_t high_alloc(unsigned long size, unsigned long align,
+			      unsigned long *addr, unsigned long max)
+{
+	unsigned long map_size, desc_size;
+	efi_memory_desc_t *map;
+	efi_status_t status;
+	unsigned long nr_pages;
+	u64 max_addr = 0;
+	int i;
+
+	status = __get_map(&map, &map_size, &desc_size);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+again:
+	for (i = 0; i < map_size / desc_size; i++) {
+		efi_memory_desc_t *desc;
+		unsigned long m = (unsigned long)map;
+		u64 start, end;
+
+		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+		if (desc->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (desc->num_pages < nr_pages)
+			continue;
+
+		start = desc->phys_addr;
+		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+		if ((start + size) > end || (start + size) > max)
+			continue;
+
+		if (end - size > max)
+			end = max;
+
+		if (round_down(end - size, align) < start)
+			continue;
+
+		start = round_down(end - size, align);
+
+		/*
+		 * Don't allocate at 0x0. It will confuse code that
+		 * checks pointers against NULL.
+		 */
+		if (start == 0x0)
+			continue;
+
+		if (start > max_addr)
+			max_addr = start;
+	}
+
+	if (!max_addr)
+		status = EFI_NOT_FOUND;
+	else {
+		status = efi_call_phys4(sys_table->boottime->allocate_pages,
+					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+					nr_pages, &max_addr);
+		if (status != EFI_SUCCESS) {
+			max = max_addr;
+			max_addr = 0;
+			goto again;
+		}
+
+		*addr = max_addr;
+	}
+
+free_pool:
+	efi_call_phys1(sys_table->boottime->free_pool, map);
+
+fail:
+	return status;
+}
+
+/*
+ * Allocate at the lowest possible address.
+ */
+static efi_status_t low_alloc(unsigned long size, unsigned long align,
+			      unsigned long *addr)
+{
+	unsigned long map_size, desc_size;
+	efi_memory_desc_t *map;
+	efi_status_t status;
+	unsigned long nr_pages;
+	int i;
+
+	status = __get_map(&map, &map_size, &desc_size);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	for (i = 0; i < map_size / desc_size; i++) {
+		efi_memory_desc_t *desc;
+		unsigned long m = (unsigned long)map;
+		u64 start, end;
+
+		desc = (efi_memory_desc_t *)(m + (i * desc_size));
+
+		if (desc->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (desc->num_pages < nr_pages)
+			continue;
+
+		start = desc->phys_addr;
+		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+		/*
+		 * Don't allocate at 0x0. It will confuse code that
+		 * checks pointers against NULL. Skip the first 8
+		 * bytes so we start at a nice even number.
+		 */
+		if (start == 0x0)
+			start += 8;
+
+		start = round_up(start, align);
+		if ((start + size) > end)
+			continue;
+
+		status = efi_call_phys4(sys_table->boottime->allocate_pages,
+					EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+					nr_pages, &start);
+		if (status == EFI_SUCCESS) {
+			*addr = start;
+			break;
+		}
+	}
+
+	if (i == map_size / desc_size)
+		status = EFI_NOT_FOUND;
+
+free_pool:
+	efi_call_phys1(sys_table->boottime->free_pool, map);
+fail:
+	return status;
+}
+
+static void low_free(unsigned long size, unsigned long addr)
+{
+	unsigned long nr_pages;
+
+	nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+	efi_call_phys2(sys_table->boottime->free_pages, addr, size);
+}
+
+static void find_bits(unsigned long mask, u8 *pos, u8 *size)
+{
+	u8 first, len;
+
+	first = 0;
+	len = 0;
+
+	if (mask) {
+		while (!(mask & 0x1)) {
+			mask = mask >> 1;
+			first++;
+		}
+
+		while (mask & 0x1) {
+			mask = mask >> 1;
+			len++;
+		}
+	}
+
+	*pos = first;
+	*size = len;
+}
+
+/*
+ * See if we have Graphics Output Protocol
+ */
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
+			      unsigned long size)
+{
+	struct efi_graphics_output_protocol *gop, *first_gop;
+	struct efi_pixel_bitmask pixel_info;
+	unsigned long nr_gops;
+	efi_status_t status;
+	void **gop_handle;
+	u16 width, height;
+	u32 fb_base, fb_size;
+	u32 pixels_per_scan_line;
+	int pixel_format;
+	int i;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, size, &gop_handle);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, proto,
+				NULL, &size, gop_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	first_gop = NULL;
+
+	nr_gops = size / sizeof(void *);
+	for (i = 0; i < nr_gops; i++) {
+		struct efi_graphics_output_mode_info *info;
+		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+		void *pciio;
+		void *h = gop_handle[i];
+
+		status = efi_call_phys3(sys_table->boottime->handle_protocol,
+					h, proto, &gop);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		efi_call_phys3(sys_table->boottime->handle_protocol,
+			       h, &pciio_proto, &pciio);
+
+		status = efi_call_phys4(gop->query_mode, gop,
+					gop->mode->mode, &size, &info);
+		if (status == EFI_SUCCESS && (!first_gop || pciio)) {
+			/*
+			 * Apple provide GOPs that are not backed by
+			 * real hardware (they're used to handle
+			 * multiple displays). The workaround is to
+			 * search for a GOP implementing the PCIIO
+			 * protocol, and if one isn't found, to just
+			 * fallback to the first GOP.
+			 */
+			width = info->horizontal_resolution;
+			height = info->vertical_resolution;
+			fb_base = gop->mode->frame_buffer_base;
+			fb_size = gop->mode->frame_buffer_size;
+			pixel_format = info->pixel_format;
+			pixel_info = info->pixel_information;
+			pixels_per_scan_line = info->pixels_per_scan_line;
+
+			/*
+			 * Once we've found a GOP supporting PCIIO,
+			 * don't bother looking any further.
+			 */
+			if (pciio)
+				break;
+
+			first_gop = gop;
+		}
+	}
+
+	/* Did we find any GOPs? */
+	if (!first_gop)
+		goto free_handle;
+
+	/* EFI framebuffer */
+	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+	si->lfb_width = width;
+	si->lfb_height = height;
+	si->lfb_base = fb_base;
+	si->lfb_size = fb_size;
+	si->pages = 1;
+
+	if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
+		si->lfb_depth = 32;
+		si->lfb_linelength = pixels_per_scan_line * 4;
+		si->red_size = 8;
+		si->red_pos = 0;
+		si->green_size = 8;
+		si->green_pos = 8;
+		si->blue_size = 8;
+		si->blue_pos = 16;
+		si->rsvd_size = 8;
+		si->rsvd_pos = 24;
+	} else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) {
+		si->lfb_depth = 32;
+		si->lfb_linelength = pixels_per_scan_line * 4;
+		si->red_size = 8;
+		si->red_pos = 16;
+		si->green_size = 8;
+		si->green_pos = 8;
+		si->blue_size = 8;
+		si->blue_pos = 0;
+		si->rsvd_size = 8;
+		si->rsvd_pos = 24;
+	} else if (pixel_format == PIXEL_BIT_MASK) {
+		find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size);
+		find_bits(pixel_info.green_mask, &si->green_pos,
+			  &si->green_size);
+		find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size);
+		find_bits(pixel_info.reserved_mask, &si->rsvd_pos,
+			  &si->rsvd_size);
+		si->lfb_depth = si->red_size + si->green_size +
+			si->blue_size + si->rsvd_size;
+		si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8;
+	} else {
+		si->lfb_depth = 4;
+		si->lfb_linelength = si->lfb_width / 2;
+		si->red_size = 0;
+		si->red_pos = 0;
+		si->green_size = 0;
+		si->green_pos = 0;
+		si->blue_size = 0;
+		si->blue_pos = 0;
+		si->rsvd_size = 0;
+		si->rsvd_pos = 0;
+	}
+
+free_handle:
+	efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+	return status;
+}
+
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
+static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+			      unsigned long size)
+{
+	struct efi_uga_draw_protocol *uga, *first_uga;
+	unsigned long nr_ugas;
+	efi_status_t status;
+	u32 width, height;
+	void **uga_handle = NULL;
+	int i;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, size, &uga_handle);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, uga_proto,
+				NULL, &size, uga_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	first_uga = NULL;
+
+	nr_ugas = size / sizeof(void *);
+	for (i = 0; i < nr_ugas; i++) {
+		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+		void *handle = uga_handle[i];
+		u32 w, h, depth, refresh;
+		void *pciio;
+
+		status = efi_call_phys3(sys_table->boottime->handle_protocol,
+					handle, uga_proto, &uga);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		efi_call_phys3(sys_table->boottime->handle_protocol,
+			       handle, &pciio_proto, &pciio);
+
+		status = efi_call_phys5(uga->get_mode, uga, &w, &h,
+					&depth, &refresh);
+		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+			width = w;
+			height = h;
+
+			/*
+			 * Once we've found a UGA supporting PCIIO,
+			 * don't bother looking any further.
+			 */
+			if (pciio)
+				break;
+
+			first_uga = uga;
+		}
+	}
+
+	if (!first_uga)
+		goto free_handle;
+
+	/* EFI framebuffer */
+	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+	si->lfb_depth = 32;
+	si->lfb_width = width;
+	si->lfb_height = height;
+
+	si->red_size = 8;
+	si->red_pos = 16;
+	si->green_size = 8;
+	si->green_pos = 8;
+	si->blue_size = 8;
+	si->blue_pos = 0;
+	si->rsvd_size = 8;
+	si->rsvd_pos = 24;
+
+
+free_handle:
+	efi_call_phys1(sys_table->boottime->free_pool, uga_handle);
+	return status;
+}
+
+void setup_graphics(struct boot_params *boot_params)
+{
+	efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID;
+	struct screen_info *si;
+	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+	efi_status_t status;
+	unsigned long size;
+	void **gop_handle = NULL;
+	void **uga_handle = NULL;
+
+	si = &boot_params->screen_info;
+	memset(si, 0, sizeof(*si));
+
+	size = 0;
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
+				NULL, &size, gop_handle);
+	if (status == EFI_BUFFER_TOO_SMALL)
+		status = setup_gop(si, &graphics_proto, size);
+
+	if (status != EFI_SUCCESS) {
+		size = 0;
+		status = efi_call_phys5(sys_table->boottime->locate_handle,
+					EFI_LOCATE_BY_PROTOCOL, &uga_proto,
+					NULL, &size, uga_handle);
+		if (status == EFI_BUFFER_TOO_SMALL)
+			setup_uga(si, &uga_proto, size);
+	}
+}
+
+struct initrd {
+	efi_file_handle_t *handle;
+	u64 size;
+};
+
+/*
+ * Check the cmdline for a LILO-style initrd= arguments.
+ *
+ * We only support loading an initrd from the same filesystem as the
+ * kernel image.
+ */
+static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
+				    struct setup_header *hdr)
+{
+	struct initrd *initrds;
+	unsigned long initrd_addr;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	u64 initrd_total;
+	efi_file_io_interface_t *io;
+	efi_file_handle_t *fh;
+	efi_status_t status;
+	int nr_initrds;
+	char *str;
+	int i, j, k;
+
+	initrd_addr = 0;
+	initrd_total = 0;
+
+	str = (char *)(unsigned long)hdr->cmd_line_ptr;
+
+	j = 0;			/* See close_handles */
+
+	if (!str || !*str)
+		return EFI_SUCCESS;
+
+	for (nr_initrds = 0; *str; nr_initrds++) {
+		str = strstr(str, "initrd=");
+		if (!str)
+			break;
+
+		str += 7;
+
+		/* Skip any leading slashes */
+		while (*str == '/' || *str == '\\')
+			str++;
+
+		while (*str && *str != ' ' && *str != '\n')
+			str++;
+	}
+
+	if (!nr_initrds)
+		return EFI_SUCCESS;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA,
+				nr_initrds * sizeof(*initrds),
+				&initrds);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	str = (char *)(unsigned long)hdr->cmd_line_ptr;
+	for (i = 0; i < nr_initrds; i++) {
+		struct initrd *initrd;
+		efi_file_handle_t *h;
+		efi_file_info_t *info;
+		efi_char16_t filename[256];
+		unsigned long info_sz;
+		efi_guid_t info_guid = EFI_FILE_INFO_ID;
+		efi_char16_t *p;
+		u64 file_sz;
+
+		str = strstr(str, "initrd=");
+		if (!str)
+			break;
+
+		str += 7;
+
+		initrd = &initrds[i];
+		p = filename;
+
+		/* Skip any leading slashes */
+		while (*str == '/' || *str == '\\')
+			str++;
+
+		while (*str && *str != ' ' && *str != '\n') {
+			if (p >= filename + sizeof(filename))
+				break;
+
+			*p++ = *str++;
+		}
+
+		*p = '\0';
+
+		/* Only open the volume once. */
+		if (!i) {
+			efi_boot_services_t *boottime;
+
+			boottime = sys_table->boottime;
+
+			status = efi_call_phys3(boottime->handle_protocol,
+					image->device_handle, &fs_proto, &io);
+			if (status != EFI_SUCCESS)
+				goto free_initrds;
+
+			status = efi_call_phys2(io->open_volume, io, &fh);
+			if (status != EFI_SUCCESS)
+				goto free_initrds;
+		}
+
+		status = efi_call_phys5(fh->open, fh, &h, filename,
+					EFI_FILE_MODE_READ, (u64)0);
+		if (status != EFI_SUCCESS)
+			goto close_handles;
+
+		initrd->handle = h;
+
+		info_sz = 0;
+		status = efi_call_phys4(h->get_info, h, &info_guid,
+					&info_sz, NULL);
+		if (status != EFI_BUFFER_TOO_SMALL)
+			goto close_handles;
+
+grow:
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+					EFI_LOADER_DATA, info_sz, &info);
+		if (status != EFI_SUCCESS)
+			goto close_handles;
+
+		status = efi_call_phys4(h->get_info, h, &info_guid,
+					&info_sz, info);
+		if (status == EFI_BUFFER_TOO_SMALL) {
+			efi_call_phys1(sys_table->boottime->free_pool, info);
+			goto grow;
+		}
+
+		file_sz = info->file_size;
+		efi_call_phys1(sys_table->boottime->free_pool, info);
+
+		if (status != EFI_SUCCESS)
+			goto close_handles;
+
+		initrd->size = file_sz;
+		initrd_total += file_sz;
+	}
+
+	if (initrd_total) {
+		unsigned long addr;
+
+		/*
+		 * Multiple initrd's need to be at consecutive
+		 * addresses in memory, so allocate enough memory for
+		 * all the initrd's.
+		 */
+		status = high_alloc(initrd_total, 0x1000,
+				   &initrd_addr, hdr->initrd_addr_max);
+		if (status != EFI_SUCCESS)
+			goto close_handles;
+
+		/* We've run out of free low memory. */
+		if (initrd_addr > hdr->initrd_addr_max) {
+			status = EFI_INVALID_PARAMETER;
+			goto free_initrd_total;
+		}
+
+		addr = initrd_addr;
+		for (j = 0; j < nr_initrds; j++) {
+			u64 size;
+
+			size = initrds[j].size;
+			status = efi_call_phys3(fh->read, initrds[j].handle,
+						&size, addr);
+			if (status != EFI_SUCCESS)
+				goto free_initrd_total;
+
+			efi_call_phys1(fh->close, initrds[j].handle);
+
+			addr += size;
+		}
+
+	}
+
+	efi_call_phys1(sys_table->boottime->free_pool, initrds);
+
+	hdr->ramdisk_image = initrd_addr;
+	hdr->ramdisk_size = initrd_total;
+
+	return status;
+
+free_initrd_total:
+	low_free(initrd_total, initrd_addr);
+
+close_handles:
+	for (k = j; k < nr_initrds; k++)
+		efi_call_phys1(fh->close, initrds[k].handle);
+free_initrds:
+	efi_call_phys1(sys_table->boottime->free_pool, initrds);
+fail:
+	hdr->ramdisk_image = 0;
+	hdr->ramdisk_size = 0;
+
+	return status;
+}
+
+/*
+ * Because the x86 boot code expects to be passed a boot_params we
+ * need to create one ourselves (usually the bootloader would create
+ * one for us).
+ */
+static efi_status_t make_boot_params(struct boot_params *boot_params,
+				     efi_loaded_image_t *image,
+				     void *handle)
+{
+	struct efi_info *efi = &boot_params->efi_info;
+	struct apm_bios_info *bi = &boot_params->apm_bios_info;
+	struct sys_desc_table *sdt = &boot_params->sys_desc_table;
+	struct e820entry *e820_map = &boot_params->e820_map[0];
+	struct e820entry *prev = NULL;
+	struct setup_header *hdr = &boot_params->hdr;
+	unsigned long size, key, desc_size, _size;
+	efi_memory_desc_t *mem_map;
+	void *options = image->load_options;
+	u32 load_options_size = image->load_options_size / 2; /* ASCII */
+	int options_size = 0;
+	efi_status_t status;
+	__u32 desc_version;
+	unsigned long cmdline;
+	u8 nr_entries;
+	u16 *s2;
+	u8 *s1;
+	int i;
+
+	hdr->type_of_loader = 0x21;
+
+	/* Convert unicode cmdline to ascii */
+	cmdline = 0;
+	s2 = (u16 *)options;
+
+	if (s2) {
+		while (*s2 && *s2 != '\n' && options_size < load_options_size) {
+			s2++;
+			options_size++;
+		}
+
+		if (options_size) {
+			if (options_size > hdr->cmdline_size)
+				options_size = hdr->cmdline_size;
+
+			options_size++;	/* NUL termination */
+
+			status = low_alloc(options_size, 1, &cmdline);
+			if (status != EFI_SUCCESS)
+				goto fail;
+
+			s1 = (u8 *)(unsigned long)cmdline;
+			s2 = (u16 *)options;
+
+			for (i = 0; i < options_size - 1; i++)
+				*s1++ = *s2++;
+
+			*s1 = '\0';
+		}
+	}
+
+	hdr->cmd_line_ptr = cmdline;
+
+	hdr->ramdisk_image = 0;
+	hdr->ramdisk_size = 0;
+
+	status = handle_ramdisks(image, hdr);
+	if (status != EFI_SUCCESS)
+		goto free_cmdline;
+
+	setup_graphics(boot_params);
+
+	/* Clear APM BIOS info */
+	memset(bi, 0, sizeof(*bi));
+
+	memset(sdt, 0, sizeof(*sdt));
+
+	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+
+	size = sizeof(*mem_map) * 32;
+
+again:
+	size += sizeof(*mem_map);
+	_size = size;
+	status = low_alloc(size, 1, (unsigned long *)&mem_map);
+	if (status != EFI_SUCCESS)
+		goto free_cmdline;
+
+	status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
+				mem_map, &key, &desc_size, &desc_version);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		low_free(_size, (unsigned long)mem_map);
+		goto again;
+	}
+
+	if (status != EFI_SUCCESS)
+		goto free_mem_map;
+
+	efi->efi_systab = (unsigned long)sys_table;
+	efi->efi_memdesc_size = desc_size;
+	efi->efi_memdesc_version = desc_version;
+	efi->efi_memmap = (unsigned long)mem_map;
+	efi->efi_memmap_size = size;
+
+#ifdef CONFIG_X86_64
+	efi->efi_systab_hi = (unsigned long)sys_table >> 32;
+	efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+#endif
+
+	/* Might as well exit boot services now */
+	status = efi_call_phys2(sys_table->boottime->exit_boot_services,
+				handle, key);
+	if (status != EFI_SUCCESS)
+		goto free_mem_map;
+
+	/* Historic? */
+	boot_params->alt_mem_k = 32 * 1024;
+
+	/*
+	 * Convert the EFI memory map to E820.
+	 */
+	nr_entries = 0;
+	for (i = 0; i < size / desc_size; i++) {
+		efi_memory_desc_t *d;
+		unsigned int e820_type = 0;
+		unsigned long m = (unsigned long)mem_map;
+
+		d = (efi_memory_desc_t *)(m + (i * desc_size));
+		switch (d->type) {
+		case EFI_RESERVED_TYPE:
+		case EFI_RUNTIME_SERVICES_CODE:
+		case EFI_RUNTIME_SERVICES_DATA:
+		case EFI_MEMORY_MAPPED_IO:
+		case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
+		case EFI_PAL_CODE:
+			e820_type = E820_RESERVED;
+			break;
+
+		case EFI_UNUSABLE_MEMORY:
+			e820_type = E820_UNUSABLE;
+			break;
+
+		case EFI_ACPI_RECLAIM_MEMORY:
+			e820_type = E820_ACPI;
+			break;
+
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+			e820_type = E820_RAM;
+			break;
+
+		case EFI_ACPI_MEMORY_NVS:
+			e820_type = E820_NVS;
+			break;
+
+		default:
+			continue;
+		}
+
+		/* Merge adjacent mappings */
+		if (prev && prev->type == e820_type &&
+		    (prev->addr + prev->size) == d->phys_addr)
+			prev->size += d->num_pages << 12;
+		else {
+			e820_map->addr = d->phys_addr;
+			e820_map->size = d->num_pages << 12;
+			e820_map->type = e820_type;
+			prev = e820_map++;
+			nr_entries++;
+		}
+	}
+
+	boot_params->e820_entries = nr_entries;
+
+	return EFI_SUCCESS;
+
+free_mem_map:
+	low_free(_size, (unsigned long)mem_map);
+free_cmdline:
+	if (options_size)
+		low_free(options_size, hdr->cmd_line_ptr);
+fail:
+	return status;
+}
+
+/*
+ * On success we return a pointer to a boot_params structure, and NULL
+ * on failure.
+ */
+struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
+{
+	struct boot_params *boot_params;
+	unsigned long start, nr_pages;
+	struct desc_ptr *gdt, *idt;
+	efi_loaded_image_t *image;
+	struct setup_header *hdr;
+	efi_status_t status;
+	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
+	struct desc_struct *desc;
+
+	sys_table = _table;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		goto fail;
+
+	status = efi_call_phys3(sys_table->boottime->handle_protocol,
+				handle, &proto, (void *)&image);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	memset(boot_params, 0x0, 0x4000);
+
+	/* Copy first two sectors to boot_params */
+	memcpy(boot_params, image->image_base, 1024);
+
+	hdr = &boot_params->hdr;
+
+	/*
+	 * The EFI firmware loader could have placed the kernel image
+	 * anywhere in memory, but the kernel has various restrictions
+	 * on the max physical address it can run at. Attempt to move
+	 * the kernel to boot_params.pref_address, or as low as
+	 * possible.
+	 */
+	start = hdr->pref_address;
+	nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+
+	status = efi_call_phys4(sys_table->boottime->allocate_pages,
+				EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+				nr_pages, &start);
+	if (status != EFI_SUCCESS) {
+		status = low_alloc(hdr->init_size, hdr->kernel_alignment,
+				   &start);
+		if (status != EFI_SUCCESS)
+			goto fail;
+	}
+
+	hdr->code32_start = (__u32)start;
+	hdr->pref_address = (__u64)(unsigned long)image->image_base;
+
+	memcpy((void *)start, image->image_base, image->image_size);
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, sizeof(*gdt),
+				(void **)&gdt);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	gdt->size = 0x800;
+	status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, sizeof(*idt),
+				(void **)&idt);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	idt->size = 0;
+	idt->address = 0;
+
+	status = make_boot_params(boot_params, image, handle);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	memset((char *)gdt->address, 0x0, gdt->size);
+	desc = (struct desc_struct *)gdt->address;
+
+	/* The first GDT is a dummy and the second is unused. */
+	desc += 2;
+
+	desc->limit0 = 0xffff;
+	desc->base0 = 0x0000;
+	desc->base1 = 0x0000;
+	desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+	desc->s = DESC_TYPE_CODE_DATA;
+	desc->dpl = 0;
+	desc->p = 1;
+	desc->limit = 0xf;
+	desc->avl = 0;
+	desc->l = 0;
+	desc->d = SEG_OP_SIZE_32BIT;
+	desc->g = SEG_GRANULARITY_4KB;
+	desc->base2 = 0x00;
+
+	desc++;
+	desc->limit0 = 0xffff;
+	desc->base0 = 0x0000;
+	desc->base1 = 0x0000;
+	desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+	desc->s = DESC_TYPE_CODE_DATA;
+	desc->dpl = 0;
+	desc->p = 1;
+	desc->limit = 0xf;
+	desc->avl = 0;
+	desc->l = 0;
+	desc->d = SEG_OP_SIZE_32BIT;
+	desc->g = SEG_GRANULARITY_4KB;
+	desc->base2 = 0x00;
+
+#ifdef CONFIG_X86_64
+	/* Task segment value */
+	desc++;
+	desc->limit0 = 0x0000;
+	desc->base0 = 0x0000;
+	desc->base1 = 0x0000;
+	desc->type = SEG_TYPE_TSS;
+	desc->s = 0;
+	desc->dpl = 0;
+	desc->p = 1;
+	desc->limit = 0x0;
+	desc->avl = 0;
+	desc->l = 0;
+	desc->d = 0;
+	desc->g = SEG_GRANULARITY_4KB;
+	desc->base2 = 0x00;
+#endif /* CONFIG_X86_64 */
+
+	asm volatile ("lidt %0" : : "m" (*idt));
+	asm volatile ("lgdt %0" : : "m" (*gdt));
+
+	asm volatile("cli");
+
+	return boot_params;
+fail:
+	return NULL;
+}
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
new file mode 100644
index 0000000..f66d023
--- /dev/null
+++ b/arch/x86/boot/compressed/eboot.h
@@ -0,0 +1,60 @@
+#ifndef BOOT_COMPRESSED_EBOOT_H
+#define BOOT_COMPRESSED_EBOOT_H
+
+#define SEG_TYPE_DATA		(0 << 3)
+#define SEG_TYPE_READ_WRITE	(1 << 1)
+#define SEG_TYPE_CODE		(1 << 3)
+#define SEG_TYPE_EXEC_READ	(1 << 1)
+#define SEG_TYPE_TSS		((1 << 3) | (1 << 0))
+#define SEG_OP_SIZE_32BIT	(1 << 0)
+#define SEG_GRANULARITY_4KB	(1 << 0)
+
+#define DESC_TYPE_CODE_DATA	(1 << 0)
+
+#define EFI_PAGE_SIZE		(1UL << EFI_PAGE_SHIFT)
+
+#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR		0
+#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR		1
+#define PIXEL_BIT_MASK					2
+#define PIXEL_BLT_ONLY					3
+#define PIXEL_FORMAT_MAX				4
+
+struct efi_pixel_bitmask {
+	u32 red_mask;
+	u32 green_mask;
+	u32 blue_mask;
+	u32 reserved_mask;
+};
+
+struct efi_graphics_output_mode_info {
+	u32 version;
+	u32 horizontal_resolution;
+	u32 vertical_resolution;
+	int pixel_format;
+	struct efi_pixel_bitmask pixel_information;
+	u32 pixels_per_scan_line;
+} __packed;
+
+struct efi_graphics_output_protocol_mode {
+	u32 max_mode;
+	u32 mode;
+	unsigned long info;
+	unsigned long size_of_info;
+	u64 frame_buffer_base;
+	unsigned long frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol {
+	void *query_mode;
+	unsigned long set_mode;
+	unsigned long blt;
+	struct efi_graphics_output_protocol_mode *mode;
+};
+
+struct efi_uga_draw_protocol {
+	void *get_mode;
+	void *set_mode;
+	void *blt;
+};
+
+#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S
new file mode 100644
index 0000000..a53440e
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_stub_32.S
@@ -0,0 +1,86 @@
+/*
+ * EFI call stub for IA32.
+ *
+ * This stub allows us to make EFI calls in physical mode with interrupts
+ * turned off. Note that this implementation is different from the one in
+ * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical
+ * mode at this point.
+ */
+
+#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 prelog and epilog.
+	 */
+
+	/*
+	 * 1. Because we haven't been relocated by this point we need to
+	 * use relative addressing.
+	 */
+	call	1f
+1:	popl	%edx
+	subl	$1b, %edx
+
+	/*
+	 * 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	%ecx
+	movl	%ecx, saved_return_addr(%edx)
+	/* get the function pointer into ECX*/
+	popl	%ecx
+	movl	%ecx, efi_rt_function_ptr(%edx)
+
+	/*
+	 * 3. Call the physical function.
+	 */
+	call	*%ecx
+
+	/*
+	 * 4. Balance the stack. And because EAX contain the return value,
+	 * we'd better not clobber it. We need to calculate our address
+	 * again because %ecx and %edx are not preserved across EFI function
+	 * calls.
+	 */
+	call	1f
+1:	popl	%edx
+	subl	$1b, %edx
+
+	movl	efi_rt_function_ptr(%edx), %ecx
+	pushl	%ecx
+
+	/*
+	 * 10. Push the saved return address onto the stack and return.
+	 */
+	movl	saved_return_addr(%edx), %ecx
+	pushl	%ecx
+	ret
+ENDPROC(efi_call_phys)
+.previous
+
+.data
+saved_return_addr:
+	.long 0
+efi_rt_function_ptr:
+	.long 0
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
new file mode 100644
index 0000000..cedc60d
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -0,0 +1 @@
+#include "../../platform/efi/efi_stub_64.S"
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 67a655a..a055993 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -32,6 +32,28 @@
 
 	__HEAD
 ENTRY(startup_32)
+#ifdef CONFIG_EFI_STUB
+	/*
+	 * We don't need the return address, so set up the stack so
+	 * efi_main() can find its arugments.
+	 */
+	add	$0x4, %esp
+
+	call	efi_main
+	cmpl	$0, %eax
+	je	preferred_addr
+	movl	%eax, %esi
+	call	1f
+1:
+	popl	%eax
+	subl	$1b, %eax
+	subl	BP_pref_address(%esi), %eax
+	add	BP_code32_start(%esi), %eax
+	leal	preferred_addr(%eax), %eax
+	jmp	*%eax
+
+preferred_addr:
+#endif
 	cld
 	/*
 	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 35af09d..558d76c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -199,6 +199,26 @@ ENTRY(startup_64)
 	 * an identity mapped page table being provied that maps our
 	 * entire text+data+bss and hopefully all of memory.
 	 */
+#ifdef CONFIG_EFI_STUB
+	pushq	%rsi
+	mov	%rcx, %rdi
+	mov	%rdx, %rsi
+	call	efi_main
+	popq	%rsi
+	cmpq	$0,%rax
+	je	preferred_addr
+	movq	%rax,%rsi
+	call	1f
+1:
+	popq	%rax
+	subq	$1b, %rax
+	subq	BP_pref_address(%rsi), %rax
+	add	BP_code32_start(%esi), %eax
+	leaq	preferred_addr(%rax), %rax
+	jmp	*%rax
+
+preferred_addr:
+#endif
 
 	/* Setup data segments. */
 	xorl	%eax, %eax
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 19b3e69..ffb9c5c 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -1,2 +1,11 @@
 #include "misc.h"
+
+int memcmp(const void *s1, const void *s2, size_t len)
+{
+	u8 diff;
+	asm("repe; cmpsb; setnz %0"
+	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	return diff;
+}
+
 #include "../string.c"