| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1313060386-4858-9-git-send-email-matt@console-pimps.org>
Date: Thu, 11 Aug 2011 11:59:45 +0100
From: Matt Fleming <matt@...sole-pimps.org>
To: linux-kernel@...r.kernel.org
Cc: "H. Peter Anvin" <hpa@...ux.intel.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...e.hu>, Mike Waychison <mikew@...gle.com>,
Matthew Garrett <mjg@...hat.com>
Subject: [PATCH 8/9] x86, efi: EFI boot stub support
From: Matt Fleming <matt.fleming@...ux.intel.com>
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
Cc: H. Peter Anvin <hpa@...ux.intel.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...e.hu>
Cc: Mike Waychison <mikew@...gle.com>
Cc: Matthew Garrett <mjg@...hat.com>
Signed-off-by: Matt Fleming <matt.fleming@...el.com>
---
arch/x86/Kconfig | 7 +
arch/x86/boot/compressed/Makefile | 10 +-
arch/x86/boot/compressed/eboot.c | 779 ++++++++++++++++++++++++++++++++
arch/x86/boot/compressed/efi_stub_32.S | 87 ++++
arch/x86/boot/compressed/efi_stub_64.S | 1 +
arch/x86/boot/compressed/head_32.S | 13 +
arch/x86/boot/compressed/head_64.S | 11 +
arch/x86/boot/compressed/string.c | 9 +
arch/x86/boot/header.S | 157 +++++++
arch/x86/boot/string.c | 35 ++
arch/x86/boot/tools/build.c | 27 ++
11 files changed, 1135 insertions(+), 1 deletions(-)
create mode 100644 arch/x86/boot/compressed/eboot.c
create mode 100644 arch/x86/boot/compressed/efi_stub_32.S
create mode 100644 arch/x86/boot/compressed/efi_stub_64.S
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a47bb2..d40c876 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1466,6 +1466,13 @@ config EFI
resultant kernel should continue to boot on existing non-EFI
platforms.
+config EFI_STUB
+ bool "EFI stub support"
+ depends on EFI
+ ---help---
+ This kernel feature allows a bzImage to be loaded directly
+ by EFI firmware without the use of a bootloader.
+
config SECCOMP
def_bool y
prompt "Enable seccomp to safely compute untrusted bytecode"
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..885568f
--- /dev/null
+++ b/arch/x86/boot/compressed/eboot.c
@@ -0,0 +1,779 @@
+/* -----------------------------------------------------------------------
+ *
+ * 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>
+
+#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
+
+typedef struct {
+ u32 red_mask;
+ u32 green_mask;
+ u32 blue_mask;
+ u32 reserved_mask;
+} efi_pixel_bitmask_t;
+
+typedef struct {
+ u32 version;
+ u32 horizontal_resolution;
+ u32 vertical_resolution;
+ int pixel_format;
+ efi_pixel_bitmask_t pixel_information;
+ u32 pixels_per_scan_line;
+} __attribute__((packed)) efi_graphics_output_mode_information_t;
+
+typedef struct {
+ u32 max_mode;
+ u32 mode;
+ unsigned long info;
+ unsigned long size_of_info;
+ u64 frame_buffer_base;
+ unsigned long frame_buffer_size;
+} __attribute__((packed)) efi_graphics_output_protocol_mode_t;
+
+typedef struct {
+ void *query_mode;
+ unsigned long set_mode;
+ unsigned long blt;
+ efi_graphics_output_protocol_mode_t *mode;
+} efi_graphics_output_protocol_t;
+
+static efi_system_table_t *sys_table;
+
+/*
+ * When the kernel decompresses itself it will expand to higher
+ * addresses. So, we need to have a way to allocate memory safely
+ * below the decompress address.
+ */
+static efi_status_t low_alloc(unsigned long size, unsigned long align,
+ unsigned long *addr)
+{
+ unsigned long map_size, key, desc_size;
+ efi_memory_desc_t *map;
+ efi_status_t status;
+ unsigned long nr_pages;
+ u32 desc_version;
+ int i;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+
+ map_size = sizeof(*map) * 32;
+
+again:
+ map_size += sizeof(*map);
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, map_size, (void **)&map);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_phys5(sys_table->boottime->get_memory_map, &map_size,
+ map, &key, &desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_phys1(sys_table->boottime->free_pool, map);
+ goto again;
+ }
+
+ if (status != EFI_SUCCESS)
+ goto free_pool;
+
+ for (i = 0; i < map_size / desc_size; i++) {
+ efi_memory_desc_t *desc;
+ u64 start, end;
+
+ desc = (efi_memory_desc_t *)((unsigned long)map + (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;
+
+ /* Check for tiny memory regions */
+ if (start >= end)
+ continue;
+ }
+
+ 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;
+}
+
+static void setup_graphics(struct boot_params *boot_params,
+ efi_guid_t *proto, void **gop_handle,
+ unsigned long size)
+{
+ efi_graphics_output_mode_information_t *info;
+ efi_graphics_output_protocol_t *gop;
+ unsigned long nr_gops;
+ struct screen_info *si;
+ efi_status_t status;
+ int i;
+
+ nr_gops = size / sizeof(void *);
+ for (i = 0; i < nr_gops; i++) {
+ void **h = &gop_handle[i];
+
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ *h, proto, &gop);
+ if (status != EFI_SUCCESS)
+ continue;
+
+ status = efi_call_phys4(gop->query_mode, gop, gop->mode->mode,
+ &size, &info);
+ if (status == EFI_SUCCESS)
+ break;
+ }
+
+ if (i == nr_gops)
+ return;
+
+ /* We found a GOP! */
+ si = &boot_params->screen_info;
+
+ si->orig_x = 0;
+ si->orig_y = 0;
+ si->orig_video_page = 0;
+ si->orig_video_mode = 0;
+ si->orig_video_cols = 0;
+ si->orig_video_ega_bx = 0;
+ si->orig_video_lines = 0;
+
+ /* EFI framebuffer */
+ si->orig_video_isVGA = 0x70;
+
+ si->orig_video_points = 0;
+
+ si->lfb_width = info->horizontal_resolution;
+ si->lfb_height = info->vertical_resolution;
+ si->lfb_base = gop->mode->frame_buffer_base;
+ si->lfb_size = gop->mode->frame_buffer_size;
+ si->pages = 1;
+ si->vesapm_seg = 0;
+ si->vesapm_off = 0;
+
+ if (info->pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
+ si->lfb_depth = 32;
+ si->lfb_linelength = info->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 (info->pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) {
+ si->lfb_depth = 32;
+ si->lfb_linelength = info->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 (info->pixel_format == PIXEL_BIT_MASK) {
+ si->lfb_linelength = (info->pixels_per_scan_line * si->lfb_depth) / 8;
+ find_bits(info->pixel_information.red_mask,
+ &si->red_pos, &si->red_size);
+ find_bits(info->pixel_information.green_mask,
+ &si->green_pos, &si->green_size);
+ find_bits(info->pixel_information.blue_mask,
+ &si->blue_pos, &si->blue_size);
+ find_bits(info->pixel_information.reserved_mask,
+ &si->rsvd_pos, &si->rsvd_size);
+ si->lfb_depth = si->red_size + si->green_size +
+ si->blue_size + si->rsvd_size;
+ } 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;
+ }
+}
+
+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++;
+
+ if (*str == ' ')
+ str++;
+ }
+
+ 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;
+
+ 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 != ' ') {
+ if (p >= filename + sizeof(filename))
+ break;
+
+ *p++ = *str++;
+ }
+
+ if (*str == ' ')
+ 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;
+ }
+
+ if (status != EFI_SUCCESS) {
+ efi_call_phys1(sys_table->boottime->free_pool, info);
+ goto close_handles;
+ }
+
+ initrd->size = info->file_size;
+ initrd_total += info->file_size;
+
+ efi_call_phys1(sys_table->boottime->free_pool, info);
+ }
+
+ 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 = low_alloc(initrd_total, 0x1000, &initrd_addr);
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ 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 screen_info *si = &boot_params->screen_info;
+ 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_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID;
+ efi_memory_desc_t *mem_map;
+ void *options = image->load_options;
+ u32 options_size = image->load_options_size;
+ void **gop_handle = NULL;
+ efi_status_t status;
+ __u32 desc_version;
+ unsigned long rows, cols;
+ unsigned int row, col, mode;
+ unsigned long cmdline;
+ u8 nr_entries;
+ u16 *s2;
+ u8 *s1;
+ int i;
+
+ hdr->type_of_loader = 0x21;
+
+ status = low_alloc(options_size, 1, &cmdline);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ hdr->cmd_line_ptr = cmdline;
+
+ /* Convert unicode cmdline to ascii */
+ s1 = (u8 *)(unsigned long)hdr->cmd_line_ptr;
+ s2 = (u16 *)options;
+
+ if (s2 && options_size) {
+ /* Skip first word, that's the kernel name */
+ while (*s2 && *s2 != ' ' && *s2 != '\n') {
+ options_size--;
+ s2++;
+ }
+
+ /* skip space */
+ if (*s2 == ' ') {
+ options_size--;
+ s2++;
+ }
+
+ while (options_size-- != 0) {
+ *s1++ = *s2++;
+ hdr->cmdline_size++;
+ }
+
+ *s1 = '\0';
+ }
+
+ hdr->ramdisk_image = 0;
+ hdr->ramdisk_size = 0;
+
+ status = handle_ramdisks(image, hdr);
+ if (status != EFI_SUCCESS)
+ goto free_cmdline;
+
+ /* See if we have graphics output protocol */
+ size = 0;
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
+ NULL, &size, gop_handle);
+
+ if (status != EFI_SUCCESS && status != EFI_BUFFER_TOO_SMALL)
+ goto free_cmdline;
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, &gop_handle);
+ if (status != EFI_SUCCESS)
+ goto free_cmdline;
+
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
+ NULL, &size, gop_handle);
+ if (status == EFI_SUCCESS)
+ setup_graphics(boot_params, &graphics_proto, gop_handle, size);
+
+ efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+
+ /* 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;
+
+ d = (efi_memory_desc_t *)((unsigned long)mem_map + (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:
+ 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)
+{
+ efi_loaded_image_t *image;
+ struct boot_params *boot_params;
+ efi_status_t status;
+ struct setup_header *hdr;
+ efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
+ struct desc_ptr *gdt, *idt;
+ u64 *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;
+ hdr->code32_start = (__u32)(unsigned long)image->image_base;
+
+ 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 = (u64 *)gdt->address;
+
+ /*
+ * 4Gb - (0x100000*0x1000 = 4Gb)
+ * base address=0
+ * code read/exec
+ * granularity=4096, 386 (+5th nibble of limit)
+ */
+ desc[2] = 0x00cf9a000000ffff;
+
+ /*
+ * 4Gb - (0x100000*0x1000 = 4Gb)
+ * base address=0
+ * data read/write
+ * granularity=4096, 386 (+5th nibble of limit)
+ */
+ desc[3] = 0x00cf92000000ffff;
+
+ /* Task segment value */
+ desc[4] = 0x0080890000000000;
+
+ 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/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S
new file mode 100644
index 0000000..5047cd9
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_stub_32.S
@@ -0,0 +1,87 @@
+/*
+ * 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..2fe23a4 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -32,6 +32,19 @@
__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 1f
+ movl %eax, %esi
+1:
+#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..09a3606 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -199,6 +199,17 @@ 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 1f
+ movq %rax,%rsi
+1:
+#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"
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 93e689f..dc2f0e9 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -45,6 +45,11 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
.global bootsect_start
bootsect_start:
+#ifdef CONFIG_EFI_STUB
+ # "MZ", MS-DOS header
+ .byte 0x4d
+ .byte 0x5a
+#endif
# Normalize the start address
ljmp $BOOTSEG, $start2
@@ -79,6 +84,14 @@ bs_die:
# invoke the BIOS reset code...
ljmp $0xf000,$0xfff0
+#ifdef CONFIG_EFI_STUB
+ .org 0x3c
+ #
+ # Offset to the PE header.
+ #
+ .long pe_header
+#endif /* CONFIG_EFI_STUB */
+
.section ".bsdata", "a"
bugger_off_msg:
.ascii "Direct booting from floppy is no longer supported.\r\n"
@@ -87,6 +100,140 @@ bugger_off_msg:
.ascii "Remove disk and press any key to reboot . . .\r\n"
.byte 0
+#ifdef CONFIG_EFI_STUB
+pe_header:
+ .ascii "PE"
+ .word 0
+
+coff_header:
+#ifdef CONFIG_X86_32
+ .word 0x14c # i386
+#else
+ .word 0x8664 # x86-64
+#endif
+ .word 2 # nr_sections
+ .long 0 # TimeDateStamp
+ .long 0 # PointerToSymbolTable
+ .long 1 # NumberOfSymbols
+ .word section_table - optional_header # SizeOfOptionalHeader
+#ifdef CONFIG_X86_32
+ .word 0x306 # Characteristics.
+ # IMAGE_FILE_32BIT_MACHINE |
+ # IMAGE_FILE_DEBUG_STRIPPED |
+ # IMAGE_FILE_EXECUTABLE_IMAGE |
+ # IMAGE_FILE_LINE_NUMS_STRIPPED
+#else
+ .word 0x206 # Characteristics
+ # IMAGE_FILE_DEBUG_STRIPPED |
+ # IMAGE_FILE_EXECUTABLE_IMAGE |
+ # IMAGE_FILE_LINE_NUMS_STRIPPED
+#endif
+
+optional_header:
+#ifdef CONFIG_X86_32
+ .word 0x10b # PE32 format
+#else
+ .word 0x20b # PE32+ format
+#endif
+ .byte 0x02 # MajorLinkerVersion
+ .byte 0x14 # MinorLinkerVersion
+ .long 0 # SizeOfCode
+ .long 0 # SizeOfInitializedData
+ .long 0 # SizeOfUninitializedData
+#ifdef CONFIG_X86_32
+ .long 0x3400 # AddressOfEntryPoint
+ .long 0x0000 # BaseOfCode
+#else
+ .long 0x3800 # AddressOfEntryPoint
+ .long 0x0000 # BaseOfCode
+#endif
+#ifdef CONFIG_X86_32
+ .long 0 # data
+#endif
+
+extra_header_fields:
+#ifdef CONFIG_X86_32
+ .long 0 # ImageBase
+#else
+ .quad 0 # ImageBase
+#endif
+ .long 0x1000 # SectionAlignment
+ .long 0x2000 # FileAlignment
+ .word 0 # MajorOperatingSystemVersion
+ .word 0 # MinorOperatingSystemVersion
+ .word 0 # MajorImageVersion
+ .word 0 # MinorImageVersion
+ .word 0 # MajorSubsystemVersion
+ .word 0 # MinorSubsystemVersion
+ .long 0 # Win32VersionValue
+
+ #
+ # The size of the bzImage is written in tools/build.c
+ #
+ .long 0 # SizeOfImage
+
+ .long 0x200 # SizeOfHeaders
+ .long 0 # CheckSum
+ .word 0xa # Subsystem (EFI application)
+ .word 0 # DllCharacteristics
+#ifdef CONFIG_X86_32
+ .long 0 # SizeOfStackReserve
+ .long 0 # SizeOfStackCommit
+ .long 0 # SizeOfHeapReserve
+ .long 0 # SizeOfHeapCommit
+#else
+ .quad 0 # SizeOfStackReserve
+ .quad 0 # SizeOfStackCommit
+ .quad 0 # SizeOfHeapReserve
+ .quad 0 # SizeOfHeapCommit
+#endif
+ .long 0 # LoaderFlags
+ .long 0x1 # NumberOfRvaAndSizes
+
+ .quad 0 # ExportTable
+ .quad 0 # ImportTable
+ .quad 0 # ResourceTable
+ .quad 0 # ExceptionTable
+ .quad 0 # CertificationTable
+ .quad 0 # BaseRelocationTable
+
+ # Section table
+section_table:
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0 # startup_{32,64}
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0 # startup_{32,64}
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x60500020 # Characteristics (section flags)
+
+ #
+ # The EFI application loader requires a relocation section
+ # because EFI applications are relocatable and not having
+ # this section seems to confuse it. But since we don't need
+ # the loader to fixup any relocs for us just fill it with a
+ # single dummy reloc.
+ #
+ .ascii ".reloc"
+ .byte 0
+ .byte 0
+ .long reloc_end - reloc_start
+ .long reloc_start
+ .long reloc_end - reloc_start # SizeOfRawData
+ .long reloc_start # PointerToRawData
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x42100040 # Characteristics (section flags)
+#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
# header, from the old boot sector.
@@ -318,3 +465,13 @@ die:
setup_corrupt:
.byte 7
.string "No setup signature found...\n"
+
+ .data
+dummy: .long 0
+
+ .section .reloc
+reloc_start:
+ .long dummy - reloc_start
+ .long 10
+ .word 0
+reloc_end:
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 3cbc405..574dedf 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -111,3 +111,38 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas
return result;
}
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t strlen(const char *s)
+{
+ const char *sc;
+
+ for (sc = s; *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+/**
+ * strstr - Find the first substring in a %NUL terminated string
+ * @s1: The string to be searched
+ * @s2: The string to search for
+ */
+char *strstr(const char *s1, const char *s2)
+{
+ size_t l1, l2;
+
+ l2 = strlen(s2);
+ if (!l2)
+ return (char *)s1;
+ l1 = strlen(s1);
+ while (l1 >= l2) {
+ l1--;
+ if (!memcmp(s1, s2, l2))
+ return (char *)s1;
+ s1++;
+ }
+ return NULL;
+}
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index fdc60a0..6088c6b 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -135,6 +135,7 @@ static void usage(void)
int main(int argc, char ** argv)
{
+ unsigned int file_sz, pe_header;
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
@@ -194,6 +195,32 @@ int main(int argc, char ** argv)
buf[0x1f6] = sys_size >> 16;
buf[0x1f7] = sys_size >> 24;
+#ifdef CONFIG_EFI_STUB
+ file_sz = sz + i + ((sys_size * 16) - sz);
+
+ pe_header = *(unsigned int *)&buf[0x3c];
+
+ /* Size of code */
+ *(unsigned int *)&buf[pe_header + 0x1c] = file_sz;
+
+ /* Size of image */
+ *(unsigned int *)&buf[pe_header + 0x50] = file_sz;
+
+#ifdef CONFIG_X86_32
+ /* .text size */
+ *(unsigned int *)&buf[pe_header + 0xb0] = file_sz;
+
+ /* .text size of initialised data */
+ *(unsigned int *)&buf[pe_header + 0xb8] = file_sz;
+#else
+ /* .text size */
+ *(unsigned int *)&buf[pe_header + 0xc0] = file_sz;
+
+ /* .text size of initialised data */
+ *(unsigned int *)&buf[pe_header + 0xc8] = file_sz;
+#endif /* CONFIG_X86_32 */
+#endif /* CONFIG_EFI_STUB */
+
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
die("Writing setup failed");
--
1.7.4.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists