diff options
Diffstat (limited to 'arch/x86/boot/compressed')
| -rw-r--r-- | arch/x86/boot/compressed/Makefile | 32 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/aslr.c | 324 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/cmdline.c | 16 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/cpuflags.c | 12 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/early_serial_console.c | 4 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/eboot.c | 1474 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/eboot.h | 122 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/efi_stub_32.S | 86 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/efi_stub_64.S | 30 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/head_32.S | 115 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/head_64.S | 191 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/misc.c | 187 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/misc.h | 53 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/mkpiggy.c | 34 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/relocs.c | 682 | ||||
| -rw-r--r-- | arch/x86/boot/compressed/string.c | 41 |
16 files changed, 2556 insertions, 847 deletions
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0c229551eea..0fcd9133790 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,8 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ + vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -12,6 +13,7 @@ KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) +KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) @@ -22,8 +24,19 @@ LDFLAGS := -m elf_$(UTS_MACHINE) LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -$(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 $(obj)/cpuflags.o $(obj)/aslr.o + +$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone + +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) @: @@ -31,13 +44,12 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) +targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs -targets += vmlinux.bin.all vmlinux.relocs relocs -hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs - +CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ - cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $< -$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE + cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $< +$(obj)/vmlinux.relocs: vmlinux FORCE $(call if_changed,relocs) vmlinux.bin.all-y := $(obj)/vmlinux.bin @@ -49,13 +61,19 @@ $(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) +$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE + $(call if_changed,xzkern) $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lz4) suffix-$(CONFIG_KERNEL_GZIP) := gz suffix-$(CONFIG_KERNEL_BZIP2) := bz2 suffix-$(CONFIG_KERNEL_LZMA) := lzma +suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo +suffix-$(CONFIG_KERNEL_LZ4) := lz4 quiet_cmd_mkpiggy = MKPIGGY $@ cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c new file mode 100644 index 00000000000..fc6091abedb --- /dev/null +++ b/arch/x86/boot/compressed/aslr.c @@ -0,0 +1,324 @@ +#include "misc.h" + +#ifdef CONFIG_RANDOMIZE_BASE +#include <asm/msr.h> +#include <asm/archrandom.h> +#include <asm/e820.h> + +#include <generated/compile.h> +#include <linux/module.h> +#include <linux/uts.h> +#include <linux/utsname.h> +#include <generated/utsrelease.h> + +/* Simplified build-specific string for starting entropy. */ +static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" + LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; + +#define I8254_PORT_CONTROL 0x43 +#define I8254_PORT_COUNTER0 0x40 +#define I8254_CMD_READBACK 0xC0 +#define I8254_SELECT_COUNTER0 0x02 +#define I8254_STATUS_NOTREADY 0x40 +static inline u16 i8254(void) +{ + u16 status, timer; + + do { + outb(I8254_PORT_CONTROL, + I8254_CMD_READBACK | I8254_SELECT_COUNTER0); + status = inb(I8254_PORT_COUNTER0); + timer = inb(I8254_PORT_COUNTER0); + timer |= inb(I8254_PORT_COUNTER0) << 8; + } while (status & I8254_STATUS_NOTREADY); + + return timer; +} + +static unsigned long rotate_xor(unsigned long hash, const void *area, + size_t size) +{ + size_t i; + unsigned long *ptr = (unsigned long *)area; + + for (i = 0; i < size / sizeof(hash); i++) { + /* Rotate by odd number of bits and XOR. */ + hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); + hash ^= ptr[i]; + } + + return hash; +} + +/* Attempt to create a simple but unpredictable starting entropy. */ +static unsigned long get_random_boot(void) +{ + unsigned long hash = 0; + + hash = rotate_xor(hash, build_str, sizeof(build_str)); + hash = rotate_xor(hash, real_mode, sizeof(*real_mode)); + + return hash; +} + +static unsigned long get_random_long(void) +{ +#ifdef CONFIG_X86_64 + const unsigned long mix_const = 0x5d6008cbf3848dd3UL; +#else + const unsigned long mix_const = 0x3f39e593UL; +#endif + unsigned long raw, random = get_random_boot(); + bool use_i8254 = true; + + debug_putstr("KASLR using"); + + if (has_cpuflag(X86_FEATURE_RDRAND)) { + debug_putstr(" RDRAND"); + if (rdrand_long(&raw)) { + random ^= raw; + use_i8254 = false; + } + } + + if (has_cpuflag(X86_FEATURE_TSC)) { + debug_putstr(" RDTSC"); + rdtscll(raw); + + random ^= raw; + use_i8254 = false; + } + + if (use_i8254) { + debug_putstr(" i8254"); + random ^= i8254(); + } + + /* Circular multiply for better bit diffusion */ + asm("mul %3" + : "=a" (random), "=d" (raw) + : "a" (random), "rm" (mix_const)); + random += raw; + + debug_putstr("...\n"); + + return random; +} + +struct mem_vector { + unsigned long start; + unsigned long size; +}; + +#define MEM_AVOID_MAX 5 +static struct mem_vector mem_avoid[MEM_AVOID_MAX]; + +static bool mem_contains(struct mem_vector *region, struct mem_vector *item) +{ + /* Item at least partially before region. */ + if (item->start < region->start) + return false; + /* Item at least partially after region. */ + if (item->start + item->size > region->start + region->size) + return false; + return true; +} + +static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) +{ + /* Item one is entirely before item two. */ + if (one->start + one->size <= two->start) + return false; + /* Item one is entirely after item two. */ + if (one->start >= two->start + two->size) + return false; + return true; +} + +static void mem_avoid_init(unsigned long input, unsigned long input_size, + unsigned long output, unsigned long output_size) +{ + u64 initrd_start, initrd_size; + u64 cmd_line, cmd_line_size; + unsigned long unsafe, unsafe_len; + char *ptr; + + /* + * Avoid the region that is unsafe to overlap during + * decompression (see calculations at top of misc.c). + */ + unsafe_len = (output_size >> 12) + 32768 + 18; + unsafe = (unsigned long)input + input_size - unsafe_len; + mem_avoid[0].start = unsafe; + mem_avoid[0].size = unsafe_len; + + /* Avoid initrd. */ + initrd_start = (u64)real_mode->ext_ramdisk_image << 32; + initrd_start |= real_mode->hdr.ramdisk_image; + initrd_size = (u64)real_mode->ext_ramdisk_size << 32; + initrd_size |= real_mode->hdr.ramdisk_size; + mem_avoid[1].start = initrd_start; + mem_avoid[1].size = initrd_size; + + /* Avoid kernel command line. */ + cmd_line = (u64)real_mode->ext_cmd_line_ptr << 32; + cmd_line |= real_mode->hdr.cmd_line_ptr; + /* Calculate size of cmd_line. */ + ptr = (char *)(unsigned long)cmd_line; + for (cmd_line_size = 0; ptr[cmd_line_size++]; ) + ; + mem_avoid[2].start = cmd_line; + mem_avoid[2].size = cmd_line_size; + + /* Avoid heap memory. */ + mem_avoid[3].start = (unsigned long)free_mem_ptr; + mem_avoid[3].size = BOOT_HEAP_SIZE; + + /* Avoid stack memory. */ + mem_avoid[4].start = (unsigned long)free_mem_end_ptr; + mem_avoid[4].size = BOOT_STACK_SIZE; +} + +/* Does this memory vector overlap a known avoided area? */ +static bool mem_avoid_overlap(struct mem_vector *img) +{ + int i; + + for (i = 0; i < MEM_AVOID_MAX; i++) { + if (mem_overlaps(img, &mem_avoid[i])) + return true; + } + + return false; +} + +static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / + CONFIG_PHYSICAL_ALIGN]; +static unsigned long slot_max; + +static void slots_append(unsigned long addr) +{ + /* Overflowing the slots list should be impossible. */ + if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET / + CONFIG_PHYSICAL_ALIGN) + return; + + slots[slot_max++] = addr; +} + +static unsigned long slots_fetch_random(void) +{ + /* Handle case of no slots stored. */ + if (slot_max == 0) + return 0; + + return slots[get_random_long() % slot_max]; +} + +static void process_e820_entry(struct e820entry *entry, + unsigned long minimum, + unsigned long image_size) +{ + struct mem_vector region, img; + + /* Skip non-RAM entries. */ + if (entry->type != E820_RAM) + return; + + /* Ignore entries entirely above our maximum. */ + if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET) + return; + + /* Ignore entries entirely below our minimum. */ + if (entry->addr + entry->size < minimum) + return; + + region.start = entry->addr; + region.size = entry->size; + + /* Potentially raise address to minimum location. */ + if (region.start < minimum) + region.start = minimum; + + /* Potentially raise address to meet alignment requirements. */ + region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); + + /* Did we raise the address above the bounds of this e820 region? */ + if (region.start > entry->addr + entry->size) + return; + + /* Reduce size by any delta from the original address. */ + region.size -= region.start - entry->addr; + + /* Reduce maximum size to fit end of image within maximum limit. */ + if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET) + region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start; + + /* Walk each aligned slot and check for avoided areas. */ + for (img.start = region.start, img.size = image_size ; + mem_contains(®ion, &img) ; + img.start += CONFIG_PHYSICAL_ALIGN) { + if (mem_avoid_overlap(&img)) + continue; + slots_append(img.start); + } +} + +static unsigned long find_random_addr(unsigned long minimum, + unsigned long size) +{ + int i; + unsigned long addr; + + /* Make sure minimum is aligned. */ + minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + + /* Verify potential e820 positions, appending to slots list. */ + for (i = 0; i < real_mode->e820_entries; i++) { + process_e820_entry(&real_mode->e820_map[i], minimum, size); + } + + return slots_fetch_random(); +} + +unsigned char *choose_kernel_location(unsigned char *input, + unsigned long input_size, + unsigned char *output, + unsigned long output_size) +{ + unsigned long choice = (unsigned long)output; + unsigned long random; + +#ifdef CONFIG_HIBERNATION + if (!cmdline_find_option_bool("kaslr")) { + debug_putstr("KASLR disabled by default...\n"); + goto out; + } +#else + if (cmdline_find_option_bool("nokaslr")) { + debug_putstr("KASLR disabled by cmdline...\n"); + goto out; + } +#endif + + /* Record the various known unsafe memory ranges. */ + mem_avoid_init((unsigned long)input, input_size, + (unsigned long)output, output_size); + + /* Walk e820 and find a random address. */ + random = find_random_addr(choice, output_size); + if (!random) { + debug_putstr("KASLR could not find suitable E820 region...\n"); + goto out; + } + + /* Always enforce the minimum. */ + if (random < choice) + goto out; + + choice = random; +out: + return (unsigned char *)choice; +} + +#endif /* CONFIG_RANDOMIZE_BASE */ diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index cb62f786990..b68e3033e6b 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,5 +1,7 @@ #include "misc.h" +#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE + static unsigned long fs; static inline void set_fs(unsigned long seg) { @@ -11,11 +13,21 @@ static inline char rdfs8(addr_t addr) return *((char *)(fs + addr)); } #include "../cmdline.c" +static unsigned long get_cmd_line_ptr(void) +{ + unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr; + + cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32; + + return cmd_line_ptr; +} int cmdline_find_option(const char *option, char *buffer, int bufsize) { - return __cmdline_find_option(real_mode->hdr.cmd_line_ptr, option, buffer, bufsize); + return __cmdline_find_option(get_cmd_line_ptr(), option, buffer, bufsize); } int cmdline_find_option_bool(const char *option) { - return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option); + return __cmdline_find_option_bool(get_cmd_line_ptr(), option); } + +#endif diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c new file mode 100644 index 00000000000..aa313466118 --- /dev/null +++ b/arch/x86/boot/compressed/cpuflags.c @@ -0,0 +1,12 @@ +#ifdef CONFIG_RANDOMIZE_BASE + +#include "../cpuflags.c" + +bool has_cpuflag(int flag) +{ + get_cpuflags(); + + return test_bit(flag, cpu.flags); +} + +#endif diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c index 261e81fb958..d3d003cb548 100644 --- a/arch/x86/boot/compressed/early_serial_console.c +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -1,5 +1,9 @@ #include "misc.h" +#ifdef CONFIG_EARLY_PRINTK + int early_serial_base; #include "../early_serial_console.c" + +#endif diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c new file mode 100644 index 00000000000..0331d765c2b --- /dev/null +++ b/arch/x86/boot/compressed/eboot.c @@ -0,0 +1,1474 @@ +/* ----------------------------------------------------------------------- + * + * 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 <linux/pci.h> +#include <asm/efi.h> +#include <asm/setup.h> +#include <asm/desc.h> + +#undef memcpy /* Use memcpy from misc.c */ + +#include "eboot.h" + +static efi_system_table_t *sys_table; + +static struct efi_config *efi_early; + +#define efi_call_early(f, ...) \ + efi_early->call(efi_early->f, __VA_ARGS__); + +#define BOOT_SERVICES(bits) \ +static void setup_boot_services##bits(struct efi_config *c) \ +{ \ + efi_system_table_##bits##_t *table; \ + efi_boot_services_##bits##_t *bt; \ + \ + table = (typeof(table))sys_table; \ + \ + c->text_output = table->con_out; \ + \ + bt = (typeof(bt))(unsigned long)(table->boottime); \ + \ + c->allocate_pool = bt->allocate_pool; \ + c->allocate_pages = bt->allocate_pages; \ + c->get_memory_map = bt->get_memory_map; \ + c->free_pool = bt->free_pool; \ + c->free_pages = bt->free_pages; \ + c->locate_handle = bt->locate_handle; \ + c->handle_protocol = bt->handle_protocol; \ + c->exit_boot_services = bt->exit_boot_services; \ +} +BOOT_SERVICES(32); +BOOT_SERVICES(64); + +static void efi_printk(efi_system_table_t *, char *); +static void efi_char16_printk(efi_system_table_t *, efi_char16_t *); + +static efi_status_t +__file_size32(void *__fh, efi_char16_t *filename_16, + void **handle, u64 *file_sz) +{ + efi_file_handle_32_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + u32 info_sz; + + status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to open file: "); + efi_char16_printk(sys_table, filename_16); + efi_printk(sys_table, "\n"); + return status; + } + + *handle = h; + + info_sz = 0; + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table, "Failed to get file info size\n"); + return status; + } + +grow: + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for file info\n"); + return status; + } + + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_early(free_pool, info); + goto grow; + } + + *file_sz = info->file_size; + efi_call_early(free_pool, info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to get initrd info\n"); + + return status; +} + +static efi_status_t +__file_size64(void *__fh, efi_char16_t *filename_16, + void **handle, u64 *file_sz) +{ + efi_file_handle_64_t *h, *fh = __fh; + efi_file_info_t *info; + efi_status_t status; + efi_guid_t info_guid = EFI_FILE_INFO_ID; + u64 info_sz; + + status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, + EFI_FILE_MODE_READ, (u64)0); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to open file: "); + efi_char16_printk(sys_table, filename_16); + efi_printk(sys_table, "\n"); + return status; + } + + *handle = h; + + info_sz = 0; + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, NULL); + if (status != EFI_BUFFER_TOO_SMALL) { + efi_printk(sys_table, "Failed to get file info size\n"); + return status; + } + +grow: + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + info_sz, (void **)&info); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for file info\n"); + return status; + } + + status = efi_early->call((unsigned long)h->get_info, h, &info_guid, + &info_sz, info); + if (status == EFI_BUFFER_TOO_SMALL) { + efi_call_early(free_pool, info); + goto grow; + } + + *file_sz = info->file_size; + efi_call_early(free_pool, info); + + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to get initrd info\n"); + + return status; +} +static efi_status_t +efi_file_size(efi_system_table_t *sys_table, void *__fh, + efi_char16_t *filename_16, void **handle, u64 *file_sz) +{ + if (efi_early->is64) + return __file_size64(__fh, filename_16, handle, file_sz); + + return __file_size32(__fh, filename_16, handle, file_sz); +} + +static inline efi_status_t +efi_file_read(void *handle, unsigned long *size, void *addr) +{ + unsigned long func; + + if (efi_early->is64) { + efi_file_handle_64_t *fh = handle; + + func = (unsigned long)fh->read; + return efi_early->call(func, handle, size, addr); + } else { + efi_file_handle_32_t *fh = handle; + + func = (unsigned long)fh->read; + return efi_early->call(func, handle, size, addr); + } +} + +static inline efi_status_t efi_file_close(void *handle) +{ + if (efi_early->is64) { + efi_file_handle_64_t *fh = handle; + + return efi_early->call((unsigned long)fh->close, handle); + } else { + efi_file_handle_32_t *fh = handle; + + return efi_early->call((unsigned long)fh->close, handle); + } +} + +static inline efi_status_t __open_volume32(void *__image, void **__fh) +{ + efi_file_io_interface_t *io; + efi_loaded_image_32_t *image = __image; + efi_file_handle_32_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)image->device_handle; + unsigned long func; + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to handle fs_proto\n"); + return status; + } + + func = (unsigned long)io->open_volume; + status = efi_early->call(func, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to open volume\n"); + + *__fh = fh; + return status; +} + +static inline efi_status_t __open_volume64(void *__image, void **__fh) +{ + efi_file_io_interface_t *io; + efi_loaded_image_64_t *image = __image; + efi_file_handle_64_t *fh; + efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID; + efi_status_t status; + void *handle = (void *)(unsigned long)image->device_handle; + unsigned long func; + + status = efi_call_early(handle_protocol, handle, + &fs_proto, (void **)&io); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to handle fs_proto\n"); + return status; + } + + func = (unsigned long)io->open_volume; + status = efi_early->call(func, io, &fh); + if (status != EFI_SUCCESS) + efi_printk(sys_table, "Failed to open volume\n"); + + *__fh = fh; + return status; +} + +static inline efi_status_t +efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) +{ + if (efi_early->is64) + return __open_volume64(__image, __fh); + + return __open_volume32(__image, __fh); +} + +static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) +{ + unsigned long output_string; + size_t offset; + + if (efi_early->is64) { + struct efi_simple_text_output_protocol_64 *out; + u64 *func; + + offset = offsetof(typeof(*out), output_string); + output_string = efi_early->text_output + offset; + func = (u64 *)output_string; + + efi_early->call(*func, efi_early->text_output, str); + } else { + struct efi_simple_text_output_protocol_32 *out; + u32 *func; + + offset = offsetof(typeof(*out), output_string); + output_string = efi_early->text_output + offset; + func = (u32 *)output_string; + + efi_early->call(*func, efi_early->text_output, str); + } +} + +#include "../../../../drivers/firmware/efi/efi-stub-helper.c" + +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 efi_status_t +__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) +{ + struct pci_setup_rom *rom = NULL; + efi_status_t status; + unsigned long size; + uint64_t attributes; + + status = efi_early->call(pci->attributes, pci, + EfiPciIoAttributeOperationGet, 0, 0, + &attributes); + if (status != EFI_SUCCESS) + return status; + + if (!pci->romimage || !pci->romsize) + return EFI_INVALID_PARAMETER; + + size = pci->romsize + sizeof(*rom); + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); + if (status != EFI_SUCCESS) + return status; + + memset(rom, 0, sizeof(*rom)); + + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; + *__rom = rom; + + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &(rom->vendor)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &(rom->devid)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->get_location, pci, &(rom->segment), + &(rom->bus), &(rom->device), &(rom->function)); + + if (status != EFI_SUCCESS) + goto free_struct; + + memcpy(rom->romdata, pci->romimage, pci->romsize); + return status; + +free_struct: + efi_call_early(free_pool, rom); + return status; +} + +static efi_status_t +setup_efi_pci32(struct boot_params *params, void **pci_handle, + unsigned long size) +{ + efi_pci_io_protocol_32 *pci = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + u32 *handles = (u32 *)(unsigned long)pci_handle; + efi_status_t status; + unsigned long nr_pci; + struct setup_data *data; + int i; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / sizeof(u32); + for (i = 0; i < nr_pci; i++) { + struct pci_setup_rom *rom = NULL; + u32 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + &pci_proto, (void **)&pci); + + if (status != EFI_SUCCESS) + continue; + + if (!pci) + continue; + + status = __setup_efi_pci32(pci, &rom); + if (status != EFI_SUCCESS) + continue; + + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; + + } + + return status; +} + +static efi_status_t +__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom) +{ + struct pci_setup_rom *rom; + efi_status_t status; + unsigned long size; + uint64_t attributes; + + status = efi_early->call(pci->attributes, pci, + EfiPciIoAttributeOperationGet, 0, + &attributes); + if (status != EFI_SUCCESS) + return status; + + if (!pci->romimage || !pci->romsize) + return EFI_INVALID_PARAMETER; + + size = pci->romsize + sizeof(*rom); + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); + if (status != EFI_SUCCESS) + return status; + + rom->data.type = SETUP_PCI; + rom->data.len = size - sizeof(struct setup_data); + rom->data.next = 0; + rom->pcilen = pci->romsize; + *__rom = rom; + + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &(rom->vendor)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &(rom->devid)); + + if (status != EFI_SUCCESS) + goto free_struct; + + status = efi_early->call(pci->get_location, pci, &(rom->segment), + &(rom->bus), &(rom->device), &(rom->function)); + + if (status != EFI_SUCCESS) + goto free_struct; + + memcpy(rom->romdata, pci->romimage, pci->romsize); + return status; + +free_struct: + efi_call_early(free_pool, rom); + return status; + +} + +static efi_status_t +setup_efi_pci64(struct boot_params *params, void **pci_handle, + unsigned long size) +{ + efi_pci_io_protocol_64 *pci = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + u64 *handles = (u64 *)(unsigned long)pci_handle; + efi_status_t status; + unsigned long nr_pci; + struct setup_data *data; + int i; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + nr_pci = size / sizeof(u64); + for (i = 0; i < nr_pci; i++) { + struct pci_setup_rom *rom = NULL; + u64 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + &pci_proto, (void **)&pci); + + if (status != EFI_SUCCESS) + continue; + + if (!pci) + continue; + + status = __setup_efi_pci64(pci, &rom); + if (status != EFI_SUCCESS) + continue; + + if (data) + data->next = (unsigned long)rom; + else + params->hdr.setup_data = (unsigned long)rom; + + data = (struct setup_data *)rom; + + } + + return status; +} + +static efi_status_t setup_efi_pci(struct boot_params *params) +{ + efi_status_t status; + void **pci_handle = NULL; + efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; + unsigned long size = 0; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); + + if (status == EFI_BUFFER_TOO_SMALL) { + status = efi_call_early(allocate_pool, + EFI_LOADER_DATA, + size, (void **)&pci_handle); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, &pci_proto, + NULL, &size, pci_handle); + } + + if (status != EFI_SUCCESS) + goto free_handle; + + if (efi_early->is64) + status = setup_efi_pci64(params, pci_handle, size); + else + status = setup_efi_pci32(params, pci_handle, size); + +free_handle: + efi_call_early(free_pool, pci_handle); + return status; +} + +static void +setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, + struct efi_pixel_bitmask pixel_info, int pixel_format) +{ + 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; + } +} + +static efi_status_t +__gop_query32(struct efi_graphics_output_protocol_32 *gop32, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u32 *fb_base) +{ + struct efi_graphics_output_protocol_mode_32 *mode; + efi_status_t status; + unsigned long m; + + m = gop32->mode; + mode = (struct efi_graphics_output_protocol_mode_32 *)m; + + status = efi_early->call(gop32->query_mode, gop32, + mode->mode, size, info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop32(struct screen_info *si, efi_guid_t *proto, + unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_32 *gop32, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status; + u32 *handles = (u32 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop32 = NULL; + + nr_gops = size / sizeof(u32); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + u32 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop32); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query32(gop32, &info, &size, &fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + 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 ConOut, + * don't bother looking any further. + */ + first_gop = gop32; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); + + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: + return status; +} + +static efi_status_t +__gop_query64(struct efi_graphics_output_protocol_64 *gop64, + struct efi_graphics_output_mode_info **info, + unsigned long *size, u32 *fb_base) +{ + struct efi_graphics_output_protocol_mode_64 *mode; + efi_status_t status; + unsigned long m; + + m = gop64->mode; + mode = (struct efi_graphics_output_protocol_mode_64 *)m; + + status = efi_early->call(gop64->query_mode, gop64, + mode->mode, size, info); + if (status != EFI_SUCCESS) + return status; + + *fb_base = mode->frame_buffer_base; + return status; +} + +static efi_status_t +setup_gop64(struct screen_info *si, efi_guid_t *proto, + unsigned long size, void **gop_handle) +{ + struct efi_graphics_output_protocol_64 *gop64, *first_gop; + unsigned long nr_gops; + u16 width, height; + u32 pixels_per_scan_line; + u32 fb_base; + struct efi_pixel_bitmask pixel_info; + int pixel_format; + efi_status_t status; + u64 *handles = (u64 *)(unsigned long)gop_handle; + int i; + + first_gop = NULL; + gop64 = NULL; + + nr_gops = size / sizeof(u64); + for (i = 0; i < nr_gops; i++) { + struct efi_graphics_output_mode_info *info = NULL; + efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; + bool conout_found = false; + void *dummy = NULL; + u64 h = handles[i]; + + status = efi_call_early(handle_protocol, h, + proto, (void **)&gop64); + if (status != EFI_SUCCESS) + continue; + + status = efi_call_early(handle_protocol, h, + &conout_proto, &dummy); + if (status == EFI_SUCCESS) + conout_found = true; + + status = __gop_query64(gop64, &info, &size, &fb_base); + if (status == EFI_SUCCESS && (!first_gop || conout_found)) { + /* + * Systems that use the UEFI Console Splitter may + * provide multiple GOP devices, not all of which are + * backed by real hardware. The workaround is to search + * for a GOP implementing the ConOut protocol, and if + * one isn't found, to just fall back to the first GOP. + */ + width = info->horizontal_resolution; + height = info->vertical_resolution; + 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 ConOut, + * don't bother looking any further. + */ + first_gop = gop64; + if (conout_found) + break; + } + } + + /* Did we find any GOPs? */ + if (!first_gop) + goto out; + + /* EFI framebuffer */ + si->orig_video_isVGA = VIDEO_TYPE_EFI; + + si->lfb_width = width; + si->lfb_height = height; + si->lfb_base = fb_base; + si->pages = 1; + + setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); + + si->lfb_size = si->lfb_linelength * si->lfb_height; + + si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; +out: + return status; +} + +/* + * See if we have Graphics Output Protocol + */ +static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, + unsigned long size) +{ + efi_status_t status; + void **gop_handle = NULL; + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&gop_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + proto, NULL, &size, gop_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + if (efi_early->is64) + status = setup_gop64(si, proto, size, gop_handle); + else + status = setup_gop32(si, proto, size, gop_handle); + +free_handle: + efi_call_early(free_pool, gop_handle); + return status; +} + +static efi_status_t +setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) +{ + struct efi_uga_draw_protocol *uga = NULL, *first_uga; + efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + unsigned long nr_ugas; + u32 *handles = (u32 *)uga_handle;; + efi_status_t status; + int i; + + first_uga = NULL; + nr_ugas = size / sizeof(u32); + for (i = 0; i < nr_ugas; i++) { + efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; + u32 w, h, depth, refresh; + void *pciio; + u32 handle = handles[i]; + + status = efi_call_early(handle_protocol, handle, + &uga_proto, (void **)&uga); + if (status != EFI_SUCCESS) + continue; + + efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); + + status = efi_early->call((unsigned long)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; + } + } + + return status; +} + +static efi_status_t +setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) +{ + struct efi_uga_draw_protocol *uga = NULL, *first_uga; + efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; + unsigned long nr_ugas; + u64 *handles = (u64 *)uga_handle;; + efi_status_t status; + int i; + + first_uga = NULL; + nr_ugas = size / sizeof(u64); + for (i = 0; i < nr_ugas; i++) { + efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; + u32 w, h, depth, refresh; + void *pciio; + u64 handle = handles[i]; + + status = efi_call_early(handle_protocol, handle, + &uga_proto, (void **)&uga); + if (status != EFI_SUCCESS) + continue; + + efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); + + status = efi_early->call((unsigned long)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; + } + } + + 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) +{ + efi_status_t status; + u32 width, height; + void **uga_handle = NULL; + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)&uga_handle); + if (status != EFI_SUCCESS) + return status; + + status = efi_call_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); + if (status != EFI_SUCCESS) + goto free_handle; + + height = 0; + width = 0; + + if (efi_early->is64) + status = setup_uga64(uga_handle, size, &width, &height); + else + status = setup_uga32(uga_handle, size, &width, &height); + + if (!width && !height) + 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_early(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_early(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_early(locate_handle, + EFI_LOCATE_BY_PROTOCOL, + &uga_proto, NULL, &size, uga_handle); + if (status == EFI_BUFFER_TOO_SMALL) + setup_uga(si, &uga_proto, size); + } +} + +/* + * 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). + * + * The caller is responsible for filling out ->code32_start in the + * returned boot_params. + */ +struct boot_params *make_boot_params(struct efi_config *c) +{ + struct boot_params *boot_params; + struct sys_desc_table *sdt; + struct apm_bios_info *bi; + struct setup_header *hdr; + struct efi_info *efi; + efi_loaded_image_t *image; + void *options, *handle; + efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; + int options_size = 0; + efi_status_t status; + char *cmdline_ptr; + u16 *s2; + u8 *s1; + int i; + unsigned long ramdisk_addr; + unsigned long ramdisk_size; + + efi_early = c; + sys_table = (efi_system_table_t *)(unsigned long)efi_early->table; + handle = (void *)(unsigned long)efi_early->image_handle; + + /* Check if we were booted by the EFI firmware */ + if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + return NULL; + + if (efi_early->is64) + setup_boot_services64(efi_early); + else + setup_boot_services32(efi_early); + + status = efi_call_early(handle_protocol, handle, + &proto, (void *)&image); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); + return NULL; + } + + status = efi_low_alloc(sys_table, 0x4000, 1, + (unsigned long *)&boot_params); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc lowmem for boot params\n"); + return NULL; + } + + memset(boot_params, 0x0, 0x4000); + + hdr = &boot_params->hdr; + efi = &boot_params->efi_info; + bi = &boot_params->apm_bios_info; + sdt = &boot_params->sys_desc_table; + + /* Copy the second sector to boot_params */ + memcpy(&hdr->jump, image->image_base + 512, 512); + + /* + * Fill out some of the header fields ourselves because the + * EFI firmware loader doesn't load the first sector. + */ + hdr->root_flags = 1; + hdr->vid_mode = 0xffff; + hdr->boot_flag = 0xAA55; + + hdr->type_of_loader = 0x21; + + /* Convert unicode cmdline to ascii */ + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); + if (!cmdline_ptr) + goto fail; + hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; + + hdr->ramdisk_image = 0; + hdr->ramdisk_size = 0; + + /* Clear APM BIOS info */ + memset(bi, 0, sizeof(*bi)); + + memset(sdt, 0, sizeof(*sdt)); + + status = handle_cmdline_files(sys_table, image, + (char *)(unsigned long)hdr->cmd_line_ptr, + "initrd=", hdr->initrd_addr_max, + &ramdisk_addr, &ramdisk_size); + if (status != EFI_SUCCESS) + goto fail2; + hdr->ramdisk_image = ramdisk_addr; + hdr->ramdisk_size = ramdisk_size; + + return boot_params; +fail2: + efi_free(sys_table, options_size, hdr->cmd_line_ptr); +fail: + efi_free(sys_table, 0x4000, (unsigned long)boot_params); + return NULL; +} + +static void add_e820ext(struct boot_params *params, + struct setup_data *e820ext, u32 nr_entries) +{ + struct setup_data *data; + efi_status_t status; + unsigned long size; + + e820ext->type = SETUP_E820_EXT; + e820ext->len = nr_entries * sizeof(struct e820entry); + e820ext->next = 0; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + if (data) + data->next = (unsigned long)e820ext; + else + params->hdr.setup_data = (unsigned long)e820ext; +} + +static efi_status_t setup_e820(struct boot_params *params, + struct setup_data *e820ext, u32 e820ext_size) +{ + struct e820entry *e820_map = ¶ms->e820_map[0]; + struct efi_info *efi = ¶ms->efi_info; + struct e820entry *prev = NULL; + u32 nr_entries; + u32 nr_desc; + int i; + + nr_entries = 0; + nr_desc = efi->efi_memmap_size / efi->efi_memdesc_size; + + for (i = 0; i < nr_desc; i++) { + efi_memory_desc_t *d; + unsigned int e820_type = 0; + unsigned long m = efi->efi_memmap; + + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_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; + continue; + } + + if (nr_entries == ARRAY_SIZE(params->e820_map)) { + u32 need = (nr_desc - i) * sizeof(struct e820entry) + + sizeof(struct setup_data); + + if (!e820ext || e820ext_size < need) + return EFI_BUFFER_TOO_SMALL; + + /* boot_params map full, switch to e820 extended */ + e820_map = (struct e820entry *)e820ext->data; + } + + e820_map->addr = d->phys_addr; + e820_map->size = d->num_pages << PAGE_SHIFT; + e820_map->type = e820_type; + prev = e820_map++; + nr_entries++; + } + + if (nr_entries > ARRAY_SIZE(params->e820_map)) { + u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map); + + add_e820ext(params, e820ext, nr_e820ext); + nr_entries -= nr_e820ext; + } + + params->e820_entries = (u8)nr_entries; + + return EFI_SUCCESS; +} + +static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, + u32 *e820ext_size) +{ + efi_status_t status; + unsigned long size; + + size = sizeof(struct setup_data) + + sizeof(struct e820entry) * nr_desc; + + if (*e820ext) { + efi_call_early(free_pool, *e820ext); + *e820ext = NULL; + *e820ext_size = 0; + } + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + size, (void **)e820ext); + if (status == EFI_SUCCESS) + *e820ext_size = size; + + return status; +} + +static efi_status_t exit_boot(struct boot_params *boot_params, + void *handle, bool is64) +{ + struct efi_info *efi = &boot_params->efi_info; + unsigned long map_sz, key, desc_size; + efi_memory_desc_t *mem_map; + struct setup_data *e820ext; + const char *signature; + __u32 e820ext_size; + __u32 nr_desc, prev_nr_desc; + efi_status_t status; + __u32 desc_version; + bool called_exit = false; + u8 nr_entries; + int i; + + nr_desc = 0; + e820ext = NULL; + e820ext_size = 0; + +get_map: + status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size, + &desc_version, &key); + + if (status != EFI_SUCCESS) + return status; + + prev_nr_desc = nr_desc; + nr_desc = map_sz / desc_size; + if (nr_desc > prev_nr_desc && + nr_desc > ARRAY_SIZE(boot_params->e820_map)) { + u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map); + + status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size); + if (status != EFI_SUCCESS) + goto free_mem_map; + + efi_call_early(free_pool, mem_map); + goto get_map; /* Allocated memory, get map again */ + } + + signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE; + memcpy(&efi->efi_loader_signature, signature, sizeof(__u32)); + + 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 = map_sz; + +#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_early(exit_boot_services, handle, key); + if (status != EFI_SUCCESS) { + /* + * ExitBootServices() will fail if any of the event + * handlers change the memory map. In which case, we + * must be prepared to retry, but only once so that + * we're guaranteed to exit on repeated failures instead + * of spinning forever. + */ + if (called_exit) + goto free_mem_map; + + called_exit = true; + efi_call_early(free_pool, mem_map); + goto get_map; + } + + /* Historic? */ + boot_params->alt_mem_k = 32 * 1024; + + status = setup_e820(boot_params, e820ext, e820ext_size); + if (status != EFI_SUCCESS) + return status; + + return EFI_SUCCESS; + +free_mem_map: + efi_call_early(free_pool, mem_map); + return status; +} + +/* + * On success we return a pointer to a boot_params structure, and NULL + * on failure. + */ +struct boot_params *efi_main(struct efi_config *c, + struct boot_params *boot_params) +{ + struct desc_ptr *gdt = NULL; + efi_loaded_image_t *image; + struct setup_header *hdr = &boot_params->hdr; + efi_status_t status; + struct desc_struct *desc; + void *handle; + efi_system_table_t *_table; + bool is64; + + efi_early = c; + + _table = (efi_system_table_t *)(unsigned long)efi_early->table; + handle = (void *)(unsigned long)efi_early->image_handle; + is64 = efi_early->is64; + + sys_table = _table; + + /* Check if we were booted by the EFI firmware */ + if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) + goto fail; + + if (is64) + setup_boot_services64(efi_early); + else + setup_boot_services32(efi_early); + + setup_graphics(boot_params); + + setup_efi_pci(boot_params); + + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, + sizeof(*gdt), (void **)&gdt); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); + goto fail; + } + + gdt->size = 0x800; + status = efi_low_alloc(sys_table, gdt->size, 8, + (unsigned long *)&gdt->address); + if (status != EFI_SUCCESS) { + efi_printk(sys_table, "Failed to alloc mem for gdt\n"); + goto fail; + } + + /* + * If the kernel isn't already loaded at the preferred load + * address, relocate it. + */ + if (hdr->pref_address != hdr->code32_start) { + unsigned long bzimage_addr = hdr->code32_start; + status = efi_relocate_kernel(sys_table, &bzimage_addr, + hdr->init_size, hdr->init_size, + hdr->pref_address, + hdr->kernel_alignment); + if (status != EFI_SUCCESS) + goto fail; + + hdr->pref_address = hdr->code32_start; + hdr->code32_start = bzimage_addr; + } + + status = exit_boot(boot_params, handle, is64); + 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("cli"); + asm volatile ("lgdt %0" : : "m" (*gdt)); + + 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 00000000000..c88c31ecad1 --- /dev/null +++ b/arch/x86/boot/compressed/eboot.h @@ -0,0 +1,122 @@ +#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_CONSOLE_OUT_DEVICE_GUID \ + EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ + 0x3f, 0xc1, 0x4d) + +#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_32 { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode_64 { + u32 max_mode; + u32 mode; + u64 info; + u64 size_of_info; + u64 frame_buffer_base; + u64 frame_buffer_size; +} __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_32 { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; +}; + +struct efi_graphics_output_protocol_64 { + u64 query_mode; + u64 set_mode; + u64 blt; + u64 mode; +}; + +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_32 { + u32 get_mode; + u32 set_mode; + u32 blt; +}; + +struct efi_uga_draw_protocol_64 { + u64 get_mode; + u64 set_mode; + u64 blt; +}; + +struct efi_uga_draw_protocol { + void *get_mode; + void *set_mode; + void *blt; +}; + +struct efi_config { + u64 image_handle; + u64 table; + u64 allocate_pool; + u64 allocate_pages; + u64 get_memory_map; + u64 free_pool; + u64 free_pages; + u64 locate_handle; + u64 handle_protocol; + u64 exit_boot_services; + u64 text_output; + efi_status_t (*call)(unsigned long, ...); + bool is64; +} __packed; + +#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 00000000000..a53440e81d5 --- /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 00000000000..7ff3632806b --- /dev/null +++ b/arch/x86/boot/compressed/efi_stub_64.S @@ -0,0 +1,30 @@ +#include <asm/segment.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> + +#include "../../platform/efi/efi_stub_64.S" + +#ifdef CONFIG_EFI_MIXED + .code64 + .text +ENTRY(efi64_thunk) + push %rbp + push %rbx + + subq $16, %rsp + leaq efi_exit32(%rip), %rax + movl %eax, 8(%rsp) + leaq efi_gdt64(%rip), %rax + movl %eax, 4(%rsp) + movl %eax, 2(%rax) /* Fixup the gdt base address */ + leaq efi32_boot_gdt(%rip), %rax + movl %eax, (%rsp) + + call __efi64_thunk + + addq $16, %rsp + pop %rbx + pop %rbp + ret +ENDPROC(efi64_thunk) +#endif /* CONFIG_EFI_MIXED */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 67a655a39ce..cbed1407a5c 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -32,6 +32,71 @@ __HEAD ENTRY(startup_32) +#ifdef CONFIG_EFI_STUB + jmp preferred_addr + + /* + * We don't need the return address, so set up the stack so + * efi_main() can find its arguments. + */ +ENTRY(efi_pe_entry) + add $0x4, %esp + + call 1f +1: popl %esi + subl $1b, %esi + + popl %ecx + movl %ecx, efi32_config(%esi) /* Handle */ + popl %ecx + movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 88(%eax) + pushl %eax + + call make_boot_params + cmpl $0, %eax + je fail + movl %esi, BP_code32_start(%eax) + popl %ecx + pushl %eax + pushl %ecx + jmp 2f /* Skip efi_config initialization */ + +ENTRY(efi32_stub_entry) + add $0x4, %esp + popl %ecx + popl %edx + + call 1f +1: popl %esi + subl $1b, %esi + + movl %ecx, efi32_config(%esi) /* Handle */ + movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 88(%eax) + pushl %eax +2: + call efi_main + cmpl $0, %eax + movl %eax, %esi + jne 2f +fail: + /* EFI init failed, so hang. */ + hlt + jmp fail +2: + movl 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 @@ -75,9 +140,11 @@ ENTRY(startup_32) addl %eax, %ebx notl %eax andl %eax, %ebx -#else - movl $LOAD_PHYSICAL_ADDR, %ebx + cmpl $LOAD_PHYSICAL_ADDR, %ebx + jge 1f #endif + movl $LOAD_PHYSICAL_ADDR, %ebx +1: /* Target address to relocate to for decompression */ addl $z_extract_offset, %ebx @@ -139,8 +206,9 @@ relocated: /* * Do the decompression, and jump to the new kernel.. */ - leal z_extract_offset_negative(%ebx), %ebp /* push arguments for decompress_kernel: */ + pushl $z_output_len /* decompressed length */ + leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax @@ -148,40 +216,23 @@ relocated: leal boot_heap(%ebx), %eax pushl %eax /* heap area */ pushl %esi /* real mode pointer */ - call decompress_kernel - addl $20, %esp - -#if CONFIG_RELOCATABLE -/* - * Find the address of the relocations. - */ - leal z_output_len(%ebp), %edi - -/* - * Calculate the delta between where vmlinux was compiled to run - * and where it was actually loaded. - */ - movl %ebp, %ebx - subl $LOAD_PHYSICAL_ADDR, %ebx - jz 2f /* Nothing to be done if loaded at compiled addr. */ -/* - * Process relocations. - */ - -1: subl $4, %edi - movl (%edi), %ecx - testl %ecx, %ecx - jz 2f - addl %ebx, -__PAGE_OFFSET(%ebx, %ecx) - jmp 1b -2: -#endif + call decompress_kernel /* returns kernel location in %eax */ + addl $24, %esp /* * Jump to the decompressed kernel. */ xorl %ebx, %ebx - jmp *%ebp + jmp *%eax + +#ifdef CONFIG_EFI_STUB + .data +efi32_config: + .fill 11,8,0 + .long efi_call_phys + .long 0 + .byte 0 +#endif /* * Stack and heap for uncompression diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 52f85a196fa..2884e0c3e8a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -27,8 +27,6 @@ #include <linux/init.h> #include <linux/linkage.h> #include <asm/segment.h> -#include <asm/pgtable_types.h> -#include <asm/page_types.h> #include <asm/boot.h> #include <asm/msr.h> #include <asm/processor-flags.h> @@ -37,6 +35,12 @@ __HEAD .code32 ENTRY(startup_32) + /* + * 32bit entry is 0 and it is ABI so immutable! + * If we come here directly from a bootloader, + * kernel(text+data+bss+brk) ramdisk, zero_page, command line + * all need to be under the 4G limit. + */ cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -46,7 +50,7 @@ ENTRY(startup_32) jnz 1f cli - movl $(__KERNEL_DS), %eax + movl $(__BOOT_DS), %eax movl %eax, %ds movl %eax, %es movl %eax, %ss @@ -90,9 +94,11 @@ ENTRY(startup_32) addl %eax, %ebx notl %eax andl %eax, %ebx -#else - movl $LOAD_PHYSICAL_ADDR, %ebx + cmpl $LOAD_PHYSICAL_ADDR, %ebx + jge 1f #endif + movl $LOAD_PHYSICAL_ADDR, %ebx +1: /* Target address to relocate to for decompression */ addl $z_extract_offset, %ebx @@ -107,7 +113,8 @@ ENTRY(startup_32) lgdt gdt(%ebp) /* Enable PAE mode */ - movl $(X86_CR4_PAE), %eax + movl %cr4, %eax + orl $X86_CR4_PAE, %eax movl %eax, %cr4 /* @@ -154,6 +161,12 @@ ENTRY(startup_32) btsl $_EFER_LME, %eax wrmsr + /* After gdt is loaded */ + xorl %eax, %eax + lldt %ax + movl $0x20, %eax + ltr %ax + /* * Setup for the jump to 64bit mode * @@ -166,6 +179,13 @@ ENTRY(startup_32) */ pushl $__KERNEL_CS leal startup_64(%ebp), %eax +#ifdef CONFIG_EFI_MIXED + movl efi32_config(%ebp), %ebx + cmp $0, %ebx + jz 1f + leal handover_entry(%ebp), %eax +1: +#endif pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -176,29 +196,102 @@ ENTRY(startup_32) lret ENDPROC(startup_32) -no_longmode: - /* This isn't an x86-64 CPU so hang */ -1: - hlt - jmp 1b +#ifdef CONFIG_EFI_MIXED + .org 0x190 +ENTRY(efi32_stub_entry) + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi -#include "../../kernel/verify_cpu_64.S" + leal (BP_scratch+4)(%esi), %esp + call 1f +1: pop %ebp + subl $1b, %ebp + + movl %ecx, efi32_config(%ebp) + movl %edx, efi32_config+8(%ebp) + sgdtl efi32_boot_gdt(%ebp) + + leal efi32_config(%ebp), %eax + movl %eax, efi_config(%ebp) + + jmp startup_32 +ENDPROC(efi32_stub_entry) +#endif - /* - * Be careful here startup_64 needs to be at a predictable - * address so I can export it in an ELF header. Bootloaders - * should look at the ELF header to find this address, as - * it may change in the future. - */ .code64 .org 0x200 ENTRY(startup_64) /* + * 64bit entry is 0x200 and it is ABI so immutable! * We come here either from startup_32 or directly from a - * 64bit bootloader. If we come here from a bootloader we depend on - * an identity mapped page table being provied that maps our - * entire text+data+bss and hopefully all of memory. + * 64bit bootloader. + * If we come here from a bootloader, kernel(text+data+bss+brk), + * ramdisk, zero_page, command line could be above 4G. + * We depend on an identity mapped page table being provided + * that maps our entire kernel(text+data+bss+brk), zero page + * and command line. + */ +#ifdef CONFIG_EFI_STUB + /* + * The entry point for the PE/COFF executable is efi_pe_entry, so + * only legacy boot loaders will execute this jmp. + */ + jmp preferred_addr + +ENTRY(efi_pe_entry) + movq %rcx, efi64_config(%rip) /* Handle */ + movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ + + leaq efi64_config(%rip), %rax + movq %rax, efi_config(%rip) + + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). + */ + addq %rbp, efi64_config+88(%rip) + + movq %rax, %rdi + call make_boot_params + cmpq $0,%rax + je fail + mov %rax, %rsi + leaq startup_32(%rip), %rax + movl %eax, BP_code32_start(%rsi) + jmp 2f /* Skip the relocation */ + +handover_entry: + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). */ + movq efi_config(%rip), %rax + addq %rbp, 88(%rax) +2: + movq efi_config(%rip), %rdi + call efi_main + movq %rax,%rsi + cmpq $0,%rax + jne 2f +fail: + /* EFI init failed, so hang. */ + hlt + jmp fail +2: + movl BP_code32_start(%esi), %eax + leaq preferred_addr(%rax), %rax + jmp *%rax + +preferred_addr: +#endif /* Setup data segments. */ xorl %eax, %eax @@ -207,9 +300,6 @@ ENTRY(startup_64) movl %eax, %ss movl %eax, %fs movl %eax, %gs - lldt %ax - movl $0x20, %eax - ltr %ax /* * Compute the decompressed kernel start address. It is where @@ -232,9 +322,11 @@ ENTRY(startup_64) addq %rax, %rbp notq %rax andq %rax, %rbp -#else - movq $LOAD_PHYSICAL_ADDR, %rbp + cmpq $LOAD_PHYSICAL_ADDR, %rbp + jge 1f #endif + movq $LOAD_PHYSICAL_ADDR, %rbp +1: /* Target address to relocate to for decompression */ leaq z_extract_offset(%rbp), %rbx @@ -266,6 +358,20 @@ ENTRY(startup_64) leaq relocated(%rbx), %rax jmp *%rax +#ifdef CONFIG_EFI_STUB + .org 0x390 +ENTRY(efi64_stub_entry) + movq %rdi, efi64_config(%rip) /* Handle */ + movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */ + + leaq efi64_config(%rip), %rax + movq %rax, efi_config(%rip) + + movq %rdx, %rsi + jmp handover_entry +ENDPROC(efi64_stub_entry) +#endif + .text relocated: @@ -301,13 +407,23 @@ relocated: leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - call decompress_kernel + movq $z_output_len, %r9 /* decompressed length */ + call decompress_kernel /* returns kernel location in %rax */ popq %rsi /* * Jump to the decompressed kernel. */ - jmp *%rbp + jmp *%rax + + .code32 +no_longmode: + /* This isn't an x86-64 CPU so hang */ +1: + hlt + jmp 1b + +#include "../../kernel/verify_cpu.S" .data gdt: @@ -321,6 +437,25 @@ gdt: .quad 0x0000000000000000 /* TS continued */ gdt_end: +#ifdef CONFIG_EFI_STUB +efi_config: + .quad 0 + +#ifdef CONFIG_EFI_MIXED + .global efi32_config +efi32_config: + .fill 11,8,0 + .quad efi64_thunk + .byte 0 +#endif + + .global efi64_config +efi64_config: + .fill 11,8,0 + .quad efi_call + .byte 1 +#endif /* CONFIG_EFI_STUB */ + /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 23f315c9f21..57ab74df7ee 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -10,6 +10,7 @@ */ #include "misc.h" +#include "../string.h" /* WARNING!! * This code is compiled with -fPIC and it is relocated dynamically @@ -97,8 +98,14 @@ */ #define STATIC static -#undef memset #undef memcpy + +/* + * Use a normal definition of memset() from string.c. There are already + * included header files which expect a definition of memset() and by + * the time we define memset macro, it is too late. + */ +#undef memset #define memzero(s, n) memset((s), 0, (n)) @@ -108,20 +115,9 @@ static void error(char *m); * This is set up by the setup-routine at boot-time */ struct boot_params *real_mode; /* Pointer to real-mode data */ -static int quiet; -static int debug; - -void *memset(void *s, int c, size_t n); -void *memcpy(void *dest, const void *src, size_t n); - -#ifdef CONFIG_X86_64 -#define memptr long -#else -#define memptr unsigned -#endif -static memptr free_mem_ptr; -static memptr free_mem_end_ptr; +memptr free_mem_ptr; +memptr free_mem_end_ptr; static char *vidmem; static int vidport; @@ -139,10 +135,18 @@ static int lines, cols; #include "../../../../lib/decompress_unlzma.c" #endif +#ifdef CONFIG_KERNEL_XZ +#include "../../../../lib/decompress_unxz.c" +#endif + #ifdef CONFIG_KERNEL_LZO #include "../../../../lib/decompress_unlzo.c" #endif +#ifdef CONFIG_KERNEL_LZ4 +#include "../../../../lib/decompress_unlz4.c" +#endif + static void scroll(void) { int i; @@ -166,15 +170,11 @@ static void serial_putchar(int ch) outb(ch, early_serial_base + TXR); } -void __putstr(int error, const char *s) +void __putstr(const char *s) { int x, y, pos; char c; -#ifndef CONFIG_X86_VERBOSE_BOOTUP - if (!error) - return; -#endif if (early_serial_base) { const char *str = s; while (*str) { @@ -220,54 +220,88 @@ void __putstr(int error, const char *s) outb(0xff & (pos >> 1), vidport+1); } -void *memset(void *s, int c, size_t n) +static void error(char *x) { - int i; - char *ss = s; + error_putstr("\n\n"); + error_putstr(x); + error_putstr("\n\n -- System halted"); - for (i = 0; i < n; i++) - ss[i] = c; - return s; -} -#ifdef CONFIG_X86_32 -void *memcpy(void *dest, const void *src, size_t n) -{ - int d0, d1, d2; - asm volatile( - "rep ; movsl\n\t" - "movl %4,%%ecx\n\t" - "rep ; movsb\n\t" - : "=&c" (d0), "=&D" (d1), "=&S" (d2) - : "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src) - : "memory"); - - return dest; -} -#else -void *memcpy(void *dest, const void *src, size_t n) -{ - long d0, d1, d2; - asm volatile( - "rep ; movsq\n\t" - "movq %4,%%rcx\n\t" - "rep ; movsb\n\t" - : "=&c" (d0), "=&D" (d1), "=&S" (d2) - : "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src) - : "memory"); - - return dest; + while (1) + asm("hlt"); } -#endif -static void error(char *x) +#if CONFIG_X86_NEED_RELOCS +static void handle_relocations(void *output, unsigned long output_len) { - __putstr(1, "\n\n"); - __putstr(1, x); - __putstr(1, "\n\n -- System halted"); + int *reloc; + unsigned long delta, map, ptr; + unsigned long min_addr = (unsigned long)output; + unsigned long max_addr = min_addr + output_len; + + /* + * Calculate the delta between where vmlinux was linked to load + * and where it was actually loaded. + */ + delta = min_addr - LOAD_PHYSICAL_ADDR; + if (!delta) { + debug_putstr("No relocation needed... "); + return; + } + debug_putstr("Performing relocations... "); + + /* + * The kernel contains a table of relocation addresses. Those + * addresses have the final load address of the kernel in virtual + * memory. We are currently working in the self map. So we need to + * create an adjustment for kernel memory addresses to the self map. + * This will involve subtracting out the base address of the kernel. + */ + map = delta - __START_KERNEL_map; + + /* + * Process relocations: 32 bit relocations first then 64 bit after. + * Two sets of binary relocations are added to the end of the kernel + * before compression. Each relocation table entry is the kernel + * address of the location which needs to be updated stored as a + * 32-bit value which is sign extended to 64 bits. + * + * Format is: + * + * kernel bits... + * 0 - zero terminator for 64 bit relocations + * 64 bit relocation repeated + * 0 - zero terminator for 32 bit relocations + * 32 bit relocation repeated + * + * So we work backwards from the end of the decompressed image. + */ + for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) { + int extended = *reloc; + extended += map; + + ptr = (unsigned long)extended; + if (ptr < min_addr || ptr > max_addr) + error("32-bit relocation outside of kernel!\n"); + + *(uint32_t *)ptr += delta; + } +#ifdef CONFIG_X86_64 + for (reloc--; *reloc; reloc--) { + long extended = *reloc; + extended += map; - while (1) - asm("hlt"); + ptr = (unsigned long)extended; + if (ptr < min_addr || ptr > max_addr) + error("64-bit relocation outside of kernel!\n"); + + *(uint64_t *)ptr += delta; + } +#endif } +#else +static inline void handle_relocations(void *output, unsigned long output_len) +{ } +#endif static void parse_elf(void *output) { @@ -290,8 +324,7 @@ static void parse_elf(void *output) return; } - if (!quiet) - putstr("Parsing ELF... "); + debug_putstr("Parsing ELF... "); phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum); if (!phdrs) @@ -317,19 +350,19 @@ static void parse_elf(void *output) default: /* Ignore other PT_* */ break; } } + + free(phdrs); } -asmlinkage void decompress_kernel(void *rmode, memptr heap, +asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, - unsigned char *output) + unsigned char *output, + unsigned long output_len) { real_mode = rmode; - if (cmdline_find_option_bool("quiet")) - quiet = 1; - if (cmdline_find_option_bool("debug")) - debug = 1; + sanitize_boot_params(real_mode); if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; @@ -343,19 +376,22 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, cols = real_mode->screen_info.orig_video_cols; console_init(); - if (debug) - putstr("early console in decompress_kernel\n"); + debug_putstr("early console in decompress_kernel\n"); free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + output = choose_kernel_location(input_data, input_len, + output, output_len); + + /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) error("Destination address inappropriately aligned"); #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); #else - if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff)) + if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); #endif #ifndef CONFIG_RELOCATABLE @@ -363,11 +399,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, error("Wrong destination address"); #endif - if (!quiet) - putstr("\nDecompressing Linux... "); + debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); - if (!quiet) - putstr("done.\nBooting the kernel.\n"); - return; + handle_relocations(output, output_len); + debug_putstr("done.\nBooting the kernel.\n"); + return output; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 3f19c81a620..24e3e569a13 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -18,22 +18,69 @@ #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> +#include <asm/bootparam_utils.h> #define BOOT_BOOT_H #include "../ctype.h" +#ifdef CONFIG_X86_64 +#define memptr long +#else +#define memptr unsigned +#endif + /* misc.c */ +extern memptr free_mem_ptr; +extern memptr free_mem_end_ptr; extern struct boot_params *real_mode; /* Pointer to real-mode data */ -void __putstr(int error, const char *s); -#define putstr(__x) __putstr(0, __x) -#define puts(__x) __putstr(0, __x) +void __putstr(const char *s); +#define error_putstr(__x) __putstr(__x) + +#ifdef CONFIG_X86_VERBOSE_BOOTUP + +#define debug_putstr(__x) __putstr(__x) +#else + +static inline void debug_putstr(const char *s) +{ } + +#endif + +#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE /* cmdline.c */ int cmdline_find_option(const char *option, char *buffer, int bufsize); int cmdline_find_option_bool(const char *option); +#endif + +#if CONFIG_RANDOMIZE_BASE +/* aslr.c */ +unsigned char *choose_kernel_location(unsigned char *input, + unsigned long input_size, + unsigned char *output, + unsigned long output_size); +/* cpuflags.c */ +bool has_cpuflag(int flag); +#else +static inline +unsigned char *choose_kernel_location(unsigned char *input, + unsigned long input_size, + unsigned char *output, + unsigned long output_size) +{ + return output; +} +#endif + +#ifdef CONFIG_EARLY_PRINTK /* early_serial_console.c */ extern int early_serial_base; void console_init(void); +#else +static const int early_serial_base; +static inline void console_init(void) +{ } +#endif #endif diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index 5c228129d17..b669ab65bf6 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -29,25 +29,19 @@ #include <stdio.h> #include <string.h> #include <inttypes.h> - -static uint32_t getle32(const void *p) -{ - const uint8_t *cp = p; - - return (uint32_t)cp[0] + ((uint32_t)cp[1] << 8) + - ((uint32_t)cp[2] << 16) + ((uint32_t)cp[3] << 24); -} +#include <tools/le_byteshift.h> int main(int argc, char *argv[]) { uint32_t olen; long ilen; unsigned long offs; - FILE *f; + FILE *f = NULL; + int retval = 1; if (argc < 2) { fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); - return 1; + goto bail; } /* Get the information for the compressed kernel image first */ @@ -55,17 +49,21 @@ int main(int argc, char *argv[]) f = fopen(argv[1], "r"); if (!f) { perror(argv[1]); - return 1; + goto bail; } if (fseek(f, -4L, SEEK_END)) { perror(argv[1]); } - fread(&olen, sizeof olen, 1, f); + + if (fread(&olen, sizeof(olen), 1, f) != 1) { + perror(argv[1]); + goto bail; + } + ilen = ftell(f); - olen = getle32(&olen); - fclose(f); + olen = get_unaligned_le32(&olen); /* * Now we have the input (compressed) and output (uncompressed) @@ -74,7 +72,7 @@ int main(int argc, char *argv[]) offs = (olen > ilen) ? olen - ilen : 0; offs += olen >> 12; /* Add 8 bytes for each 32K block */ - offs += 32*1024 + 18; /* Add 32K + 18 bytes slack */ + offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ printf(".section \".rodata..compressed\",\"a\",@progbits\n"); @@ -93,5 +91,9 @@ int main(int argc, char *argv[]) printf(".incbin \"%s\"\n", argv[1]); printf("input_data_end:\n"); - return 0; + retval = 0; +bail: + if (f) + fclose(f); + return retval; } diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c deleted file mode 100644 index 89bbf4e4d05..00000000000 --- a/arch/x86/boot/compressed/relocs.c +++ /dev/null @@ -1,682 +0,0 @@ -#include <stdio.h> -#include <stdarg.h> -#include <stdlib.h> -#include <stdint.h> -#include <string.h> -#include <errno.h> -#include <unistd.h> -#include <elf.h> -#include <byteswap.h> -#define USE_BSD -#include <endian.h> -#include <regex.h> - -static void die(char *fmt, ...); - -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -static Elf32_Ehdr ehdr; -static unsigned long reloc_count, reloc_idx; -static unsigned long *relocs; - -struct section { - Elf32_Shdr shdr; - struct section *link; - Elf32_Sym *symtab; - Elf32_Rel *reltab; - char *strtab; -}; -static struct section *secs; - -/* - * Following symbols have been audited. There values are constant and do - * not change if bzImage is loaded at a different physical address than - * the address for which it has been compiled. Don't warn user about - * absolute relocations present w.r.t these symbols. - */ -static const char abs_sym_regex[] = - "^(xen_irq_disable_direct_reloc$|" - "xen_save_fl_direct_reloc$|" - "VDSO|" - "__crc_)"; -static regex_t abs_sym_regex_c; -static int is_abs_reloc(const char *sym_name) -{ - return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0); -} - -/* - * These symbols are known to be relative, even if the linker marks them - * as absolute (typically defined outside any section in the linker script.) - */ -static const char rel_sym_regex[] = - "^_end$"; -static regex_t rel_sym_regex_c; -static int is_rel_reloc(const char *sym_name) -{ - return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0); -} - -static void regex_init(void) -{ - char errbuf[128]; - int err; - - err = regcomp(&abs_sym_regex_c, abs_sym_regex, - REG_EXTENDED|REG_NOSUB); - if (err) { - regerror(err, &abs_sym_regex_c, errbuf, sizeof errbuf); - die("%s", errbuf); - } - - err = regcomp(&rel_sym_regex_c, rel_sym_regex, - REG_EXTENDED|REG_NOSUB); - if (err) { - regerror(err, &rel_sym_regex_c, errbuf, sizeof errbuf); - die("%s", errbuf); - } -} - -static void die(char *fmt, ...) -{ - va_list ap; - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); - va_end(ap); - exit(1); -} - -static const char *sym_type(unsigned type) -{ - static const char *type_name[] = { -#define SYM_TYPE(X) [X] = #X - SYM_TYPE(STT_NOTYPE), - SYM_TYPE(STT_OBJECT), - SYM_TYPE(STT_FUNC), - SYM_TYPE(STT_SECTION), - SYM_TYPE(STT_FILE), - SYM_TYPE(STT_COMMON), - SYM_TYPE(STT_TLS), -#undef SYM_TYPE - }; - const char *name = "unknown sym type name"; - if (type < ARRAY_SIZE(type_name)) { - name = type_name[type]; - } - return name; -} - -static const char *sym_bind(unsigned bind) -{ - static const char *bind_name[] = { -#define SYM_BIND(X) [X] = #X - SYM_BIND(STB_LOCAL), - SYM_BIND(STB_GLOBAL), - SYM_BIND(STB_WEAK), -#undef SYM_BIND - }; - const char *name = "unknown sym bind name"; - if (bind < ARRAY_SIZE(bind_name)) { - name = bind_name[bind]; - } - return name; -} - -static const char *sym_visibility(unsigned visibility) -{ - static const char *visibility_name[] = { -#define SYM_VISIBILITY(X) [X] = #X - SYM_VISIBILITY(STV_DEFAULT), - SYM_VISIBILITY(STV_INTERNAL), - SYM_VISIBILITY(STV_HIDDEN), - SYM_VISIBILITY(STV_PROTECTED), -#undef SYM_VISIBILITY - }; - const char *name = "unknown sym visibility name"; - if (visibility < ARRAY_SIZE(visibility_name)) { - name = visibility_name[visibility]; - } - return name; -} - -static const char *rel_type(unsigned type) -{ - static const char *type_name[] = { -#define REL_TYPE(X) [X] = #X - REL_TYPE(R_386_NONE), - REL_TYPE(R_386_32), - REL_TYPE(R_386_PC32), - REL_TYPE(R_386_GOT32), - REL_TYPE(R_386_PLT32), - REL_TYPE(R_386_COPY), - REL_TYPE(R_386_GLOB_DAT), - REL_TYPE(R_386_JMP_SLOT), - REL_TYPE(R_386_RELATIVE), - REL_TYPE(R_386_GOTOFF), - REL_TYPE(R_386_GOTPC), -#undef REL_TYPE - }; - const char *name = "unknown type rel type name"; - if (type < ARRAY_SIZE(type_name) && type_name[type]) { - name = type_name[type]; - } - return name; -} - -static const char *sec_name(unsigned shndx) -{ - const char *sec_strtab; - const char *name; - sec_strtab = secs[ehdr.e_shstrndx].strtab; - name = "<noname>"; - if (shndx < ehdr.e_shnum) { - name = sec_strtab + secs[shndx].shdr.sh_name; - } - else if (shndx == SHN_ABS) { - name = "ABSOLUTE"; - } - else if (shndx == SHN_COMMON) { - name = "COMMON"; - } - return name; -} - -static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) -{ - const char *name; - name = "<noname>"; - if (sym->st_name) { - name = sym_strtab + sym->st_name; - } - else { - name = sec_name(secs[sym->st_shndx].shdr.sh_name); - } - return name; -} - - - -#if BYTE_ORDER == LITTLE_ENDIAN -#define le16_to_cpu(val) (val) -#define le32_to_cpu(val) (val) -#endif -#if BYTE_ORDER == BIG_ENDIAN -#define le16_to_cpu(val) bswap_16(val) -#define le32_to_cpu(val) bswap_32(val) -#endif - -static uint16_t elf16_to_cpu(uint16_t val) -{ - return le16_to_cpu(val); -} - -static uint32_t elf32_to_cpu(uint32_t val) -{ - return le32_to_cpu(val); -} - -static void read_ehdr(FILE *fp) -{ - if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) { - die("Cannot read ELF header: %s\n", - strerror(errno)); - } - if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) { - die("No ELF magic\n"); - } - if (ehdr.e_ident[EI_CLASS] != ELFCLASS32) { - die("Not a 32 bit executable\n"); - } - if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB) { - die("Not a LSB ELF executable\n"); - } - if (ehdr.e_ident[EI_VERSION] != EV_CURRENT) { - die("Unknown ELF version\n"); - } - /* Convert the fields to native endian */ - ehdr.e_type = elf16_to_cpu(ehdr.e_type); - ehdr.e_machine = elf16_to_cpu(ehdr.e_machine); - ehdr.e_version = elf32_to_cpu(ehdr.e_version); - ehdr.e_entry = elf32_to_cpu(ehdr.e_entry); - ehdr.e_phoff = elf32_to_cpu(ehdr.e_phoff); - ehdr.e_shoff = elf32_to_cpu(ehdr.e_shoff); - ehdr.e_flags = elf32_to_cpu(ehdr.e_flags); - ehdr.e_ehsize = elf16_to_cpu(ehdr.e_ehsize); - ehdr.e_phentsize = elf16_to_cpu(ehdr.e_phentsize); - ehdr.e_phnum = elf16_to_cpu(ehdr.e_phnum); - ehdr.e_shentsize = elf16_to_cpu(ehdr.e_shentsize); - ehdr.e_shnum = elf16_to_cpu(ehdr.e_shnum); - ehdr.e_shstrndx = elf16_to_cpu(ehdr.e_shstrndx); - - if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) { - die("Unsupported ELF header type\n"); - } - if (ehdr.e_machine != EM_386) { - die("Not for x86\n"); - } - if (ehdr.e_version != EV_CURRENT) { - die("Unknown ELF version\n"); - } - if (ehdr.e_ehsize != sizeof(Elf32_Ehdr)) { - die("Bad Elf header size\n"); - } - if (ehdr.e_phentsize != sizeof(Elf32_Phdr)) { - die("Bad program header entry\n"); - } - if (ehdr.e_shentsize != sizeof(Elf32_Shdr)) { - die("Bad section header entry\n"); - } - if (ehdr.e_shstrndx >= ehdr.e_shnum) { - die("String table index out of bounds\n"); - } -} - -static void read_shdrs(FILE *fp) -{ - int i; - Elf32_Shdr shdr; - - secs = calloc(ehdr.e_shnum, sizeof(struct section)); - if (!secs) { - die("Unable to allocate %d section headers\n", - ehdr.e_shnum); - } - if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - ehdr.e_shoff, strerror(errno)); - } - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - if (fread(&shdr, sizeof shdr, 1, fp) != 1) - die("Cannot read ELF section headers %d/%d: %s\n", - i, ehdr.e_shnum, strerror(errno)); - sec->shdr.sh_name = elf32_to_cpu(shdr.sh_name); - sec->shdr.sh_type = elf32_to_cpu(shdr.sh_type); - sec->shdr.sh_flags = elf32_to_cpu(shdr.sh_flags); - sec->shdr.sh_addr = elf32_to_cpu(shdr.sh_addr); - sec->shdr.sh_offset = elf32_to_cpu(shdr.sh_offset); - sec->shdr.sh_size = elf32_to_cpu(shdr.sh_size); - sec->shdr.sh_link = elf32_to_cpu(shdr.sh_link); - sec->shdr.sh_info = elf32_to_cpu(shdr.sh_info); - sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign); - sec->shdr.sh_entsize = elf32_to_cpu(shdr.sh_entsize); - if (sec->shdr.sh_link < ehdr.e_shnum) - sec->link = &secs[sec->shdr.sh_link]; - } - -} - -static void read_strtabs(FILE *fp) -{ - int i; - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_STRTAB) { - continue; - } - sec->strtab = malloc(sec->shdr.sh_size); - if (!sec->strtab) { - die("malloc of %d bytes for strtab failed\n", - sec->shdr.sh_size); - } - if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); - } - if (fread(sec->strtab, 1, sec->shdr.sh_size, fp) - != sec->shdr.sh_size) { - die("Cannot read symbol table: %s\n", - strerror(errno)); - } - } -} - -static void read_symtabs(FILE *fp) -{ - int i,j; - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_SYMTAB) { - continue; - } - sec->symtab = malloc(sec->shdr.sh_size); - if (!sec->symtab) { - die("malloc of %d bytes for symtab failed\n", - sec->shdr.sh_size); - } - if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); - } - if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) - != sec->shdr.sh_size) { - die("Cannot read symbol table: %s\n", - strerror(errno)); - } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym = &sec->symtab[j]; - sym->st_name = elf32_to_cpu(sym->st_name); - sym->st_value = elf32_to_cpu(sym->st_value); - sym->st_size = elf32_to_cpu(sym->st_size); - sym->st_shndx = elf16_to_cpu(sym->st_shndx); - } - } -} - - -static void read_relocs(FILE *fp) -{ - int i,j; - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_REL) { - continue; - } - sec->reltab = malloc(sec->shdr.sh_size); - if (!sec->reltab) { - die("malloc of %d bytes for relocs failed\n", - sec->shdr.sh_size); - } - if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %d failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); - } - if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) - != sec->shdr.sh_size) { - die("Cannot read symbol table: %s\n", - strerror(errno)); - } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel = &sec->reltab[j]; - rel->r_offset = elf32_to_cpu(rel->r_offset); - rel->r_info = elf32_to_cpu(rel->r_info); - } - } -} - - -static void print_absolute_symbols(void) -{ - int i; - printf("Absolute symbols\n"); - printf(" Num: Value Size Type Bind Visibility Name\n"); - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - char *sym_strtab; - Elf32_Sym *sh_symtab; - int j; - - if (sec->shdr.sh_type != SHT_SYMTAB) { - continue; - } - sh_symtab = sec->symtab; - sym_strtab = sec->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym; - const char *name; - sym = &sec->symtab[j]; - name = sym_name(sym_strtab, sym); - if (sym->st_shndx != SHN_ABS) { - continue; - } - printf("%5d %08x %5d %10s %10s %12s %s\n", - j, sym->st_value, sym->st_size, - sym_type(ELF32_ST_TYPE(sym->st_info)), - sym_bind(ELF32_ST_BIND(sym->st_info)), - sym_visibility(ELF32_ST_VISIBILITY(sym->st_other)), - name); - } - } - printf("\n"); -} - -static void print_absolute_relocs(void) -{ - int i, printed = 0; - - for (i = 0; i < ehdr.e_shnum; i++) { - struct section *sec = &secs[i]; - struct section *sec_applies, *sec_symtab; - char *sym_strtab; - Elf32_Sym *sh_symtab; - int j; - if (sec->shdr.sh_type != SHT_REL) { - continue; - } - sec_symtab = sec->link; - sec_applies = &secs[sec->shdr.sh_info]; - if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { - continue; - } - sh_symtab = sec_symtab->symtab; - sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; - const char *name; - rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; - name = sym_name(sym_strtab, sym); - if (sym->st_shndx != SHN_ABS) { - continue; - } - - /* Absolute symbols are not relocated if bzImage is - * loaded at a non-compiled address. Display a warning - * to user at compile time about the absolute - * relocations present. - * - * User need to audit the code to make sure - * some symbols which should have been section - * relative have not become absolute because of some - * linker optimization or wrong programming usage. - * - * Before warning check if this absolute symbol - * relocation is harmless. - */ - if (is_abs_reloc(name) || is_rel_reloc(name)) - continue; - - if (!printed) { - printf("WARNING: Absolute relocations" - " present\n"); - printf("Offset Info Type Sym.Value " - "Sym.Name\n"); - printed = 1; - } - - printf("%08x %08x %10s %08x %s\n", - rel->r_offset, - rel->r_info, - rel_type(ELF32_R_TYPE(rel->r_info)), - sym->st_value, - name); - } - } - - if (printed) - printf("\n"); -} - -static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) -{ - int i; - /* Walk through the relocations */ - for (i = 0; i < ehdr.e_shnum; i++) { - char *sym_strtab; - Elf32_Sym *sh_symtab; - struct section *sec_applies, *sec_symtab; - int j; - struct section *sec = &secs[i]; - - if (sec->shdr.sh_type != SHT_REL) { - continue; - } - sec_symtab = sec->link; - sec_applies = &secs[sec->shdr.sh_info]; - if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { - continue; - } - sh_symtab = sec_symtab->symtab; - sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; - unsigned r_type; - rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; - r_type = ELF32_R_TYPE(rel->r_info); - /* Don't visit relocations to absolute symbols */ - if (sym->st_shndx == SHN_ABS && - !is_rel_reloc(sym_name(sym_strtab, sym))) { - continue; - } - switch (r_type) { - case R_386_NONE: - case R_386_PC32: - /* - * NONE can be ignored and and PC relative - * relocations don't need to be adjusted. - */ - break; - case R_386_32: - /* Visit relocations that need to be adjusted */ - visit(rel, sym); - break; - default: - die("Unsupported relocation type: %s (%d)\n", - rel_type(r_type), r_type); - break; - } - } - } -} - -static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym) -{ - reloc_count += 1; -} - -static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym) -{ - /* Remember the address that needs to be adjusted. */ - relocs[reloc_idx++] = rel->r_offset; -} - -static int cmp_relocs(const void *va, const void *vb) -{ - const unsigned long *a, *b; - a = va; b = vb; - return (*a == *b)? 0 : (*a > *b)? 1 : -1; -} - -static void emit_relocs(int as_text) -{ - int i; - /* Count how many relocations I have and allocate space for them. */ - reloc_count = 0; - walk_relocs(count_reloc); - relocs = malloc(reloc_count * sizeof(relocs[0])); - if (!relocs) { - die("malloc of %d entries for relocs failed\n", - reloc_count); - } - /* Collect up the relocations */ - reloc_idx = 0; - walk_relocs(collect_reloc); - - /* Order the relocations for more efficient processing */ - qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs); - - /* Print the relocations */ - if (as_text) { - /* Print the relocations in a form suitable that - * gas will like. - */ - printf(".section \".data.reloc\",\"a\"\n"); - printf(".balign 4\n"); - for (i = 0; i < reloc_count; i++) { - printf("\t .long 0x%08lx\n", relocs[i]); - } - printf("\n"); - } - else { - unsigned char buf[4]; - /* Print a stop */ - fwrite("\0\0\0\0", 4, 1, stdout); - /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) { - buf[0] = (relocs[i] >> 0) & 0xff; - buf[1] = (relocs[i] >> 8) & 0xff; - buf[2] = (relocs[i] >> 16) & 0xff; - buf[3] = (relocs[i] >> 24) & 0xff; - fwrite(buf, 4, 1, stdout); - } - } -} - -static void usage(void) -{ - die("relocs [--abs-syms |--abs-relocs | --text] vmlinux\n"); -} - -int main(int argc, char **argv) -{ - int show_absolute_syms, show_absolute_relocs; - int as_text; - const char *fname; - FILE *fp; - int i; - - regex_init(); - - show_absolute_syms = 0; - show_absolute_relocs = 0; - as_text = 0; - fname = NULL; - for (i = 1; i < argc; i++) { - char *arg = argv[i]; - if (*arg == '-') { - if (strcmp(argv[1], "--abs-syms") == 0) { - show_absolute_syms = 1; - continue; - } - - if (strcmp(argv[1], "--abs-relocs") == 0) { - show_absolute_relocs = 1; - continue; - } - else if (strcmp(argv[1], "--text") == 0) { - as_text = 1; - continue; - } - } - else if (!fname) { - fname = arg; - continue; - } - usage(); - } - if (!fname) { - usage(); - } - fp = fopen(fname, "r"); - if (!fp) { - die("Cannot open %s: %s\n", - fname, strerror(errno)); - } - read_ehdr(fp); - read_shdrs(fp); - read_strtabs(fp); - read_symtabs(fp); - read_relocs(fp); - if (show_absolute_syms) { - print_absolute_symbols(); - return 0; - } - if (show_absolute_relocs) { - print_absolute_relocs(); - return 0; - } - emit_relocs(as_text); - return 0; -} diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index 19b3e693cd7..00e788be1db 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,2 +1,41 @@ -#include "misc.h" #include "../string.c" + +#ifdef CONFIG_X86_32 +void *memcpy(void *dest, const void *src, size_t n) +{ + int d0, d1, d2; + asm volatile( + "rep ; movsl\n\t" + "movl %4,%%ecx\n\t" + "rep ; movsb\n\t" + : "=&c" (d0), "=&D" (d1), "=&S" (d2) + : "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src) + : "memory"); + + return dest; +} +#else +void *memcpy(void *dest, const void *src, size_t n) +{ + long d0, d1, d2; + asm volatile( + "rep ; movsq\n\t" + "movq %4,%%rcx\n\t" + "rep ; movsb\n\t" + : "=&c" (d0), "=&D" (d1), "=&S" (d2) + : "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src) + : "memory"); + + return dest; +} +#endif + +void *memset(void *s, int c, size_t n) +{ + int i; + char *ss = s; + + for (i = 0; i < n; i++) + ss[i] = c; + return s; +} |