aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/boot/compressed
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/boot/compressed')
-rw-r--r--arch/x86/boot/compressed/.gitignore1
-rw-r--r--arch/x86/boot/compressed/Makefile5
-rw-r--r--arch/x86/boot/compressed/Makefile_3250
-rw-r--r--arch/x86/boot/compressed/Makefile_6430
-rw-r--r--arch/x86/boot/compressed/head_32.S180
-rw-r--r--arch/x86/boot/compressed/head_64.S311
-rw-r--r--arch/x86/boot/compressed/misc_32.c379
-rw-r--r--arch/x86/boot/compressed/misc_64.c371
-rw-r--r--arch/x86/boot/compressed/relocs.c631
-rw-r--r--arch/x86/boot/compressed/vmlinux_32.lds43
-rw-r--r--arch/x86/boot/compressed/vmlinux_32.scr10
-rw-r--r--arch/x86/boot/compressed/vmlinux_64.lds44
-rw-r--r--arch/x86/boot/compressed/vmlinux_64.scr10
13 files changed, 2065 insertions, 0 deletions
diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore
new file mode 100644
index 000000000000..be0ed065249b
--- /dev/null
+++ b/arch/x86/boot/compressed/.gitignore
@@ -0,0 +1 @@
+relocs
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
new file mode 100644
index 000000000000..52c1db854520
--- /dev/null
+++ b/arch/x86/boot/compressed/Makefile
@@ -0,0 +1,5 @@
+ifeq ($(CONFIG_X86_32),y)
+include ${srctree}/arch/x86/boot/compressed/Makefile_32
+else
+include ${srctree}/arch/x86/boot/compressed/Makefile_64
+endif
diff --git a/arch/x86/boot/compressed/Makefile_32 b/arch/x86/boot/compressed/Makefile_32
new file mode 100644
index 000000000000..22613c652d22
--- /dev/null
+++ b/arch/x86/boot/compressed/Makefile_32
@@ -0,0 +1,50 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets := vmlinux vmlinux.bin vmlinux.bin.gz head_32.o misc_32.o piggy.o \
+ vmlinux.bin.all vmlinux.relocs
+EXTRA_AFLAGS := -traditional
+
+LDFLAGS_vmlinux := -T
+hostprogs-y := relocs
+
+CFLAGS := -m32 -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
+ -fno-strict-aliasing -fPIC \
+ $(call cc-option,-ffreestanding) \
+ $(call cc-option,-fno-stack-protector)
+LDFLAGS := -m elf_i386
+
+$(obj)/vmlinux: $(src)/vmlinux_32.lds $(obj)/head_32.o $(obj)/misc_32.o $(obj)/piggy.o FORCE
+ $(call if_changed,ld)
+ @:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+ $(call if_changed,objcopy)
+
+quiet_cmd_relocs = RELOCS $@
+ cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
+ $(call if_changed,relocs)
+
+vmlinux.bin.all-y := $(obj)/vmlinux.bin
+vmlinux.bin.all-$(CONFIG_RELOCATABLE) += $(obj)/vmlinux.relocs
+quiet_cmd_relocbin = BUILD $@
+ cmd_relocbin = cat $(filter-out FORCE,$^) > $@
+$(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
+ $(call if_changed,relocbin)
+
+ifdef CONFIG_RELOCATABLE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
+ $(call if_changed,gzip)
+else
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,gzip)
+endif
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
+
+$(obj)/piggy.o: $(src)/vmlinux_32.scr $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/Makefile_64 b/arch/x86/boot/compressed/Makefile_64
new file mode 100644
index 000000000000..dc6b3380cc45
--- /dev/null
+++ b/arch/x86/boot/compressed/Makefile_64
@@ -0,0 +1,30 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets := vmlinux vmlinux.bin vmlinux.bin.gz head_64.o misc_64.o piggy.o
+
+CFLAGS := -m64 -D__KERNEL__ $(LINUXINCLUDE) -O2 \
+ -fno-strict-aliasing -fPIC -mcmodel=small \
+ $(call cc-option, -ffreestanding) \
+ $(call cc-option, -fno-stack-protector)
+AFLAGS := $(CFLAGS) -D__ASSEMBLY__
+LDFLAGS := -m elf_x86_64
+
+LDFLAGS_vmlinux := -T
+$(obj)/vmlinux: $(src)/vmlinux_64.lds $(obj)/head_64.o $(obj)/misc_64.o $(obj)/piggy.o FORCE
+ $(call if_changed,ld)
+ @:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+ $(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,gzip)
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
+
+$(obj)/piggy.o: $(obj)/vmlinux_64.scr $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
new file mode 100644
index 000000000000..f35ea2237522
--- /dev/null
+++ b/arch/x86/boot/compressed/head_32.S
@@ -0,0 +1,180 @@
+/*
+ * linux/boot/head.S
+ *
+ * Copyright (C) 1991, 1992, 1993 Linus Torvalds
+ */
+
+/*
+ * head.S contains the 32-bit startup code.
+ *
+ * NOTE!!! Startup happens at absolute address 0x00001000, which is also where
+ * the page directory will exist. The startup code will be overwritten by
+ * the page directory. [According to comments etc elsewhere on a compressed
+ * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
+ *
+ * Page 0 is deliberately kept safe, since System Management Mode code in
+ * laptops may need to access the BIOS data stored there. This is also
+ * useful for future device drivers that either access the BIOS via VM86
+ * mode.
+ */
+
+/*
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+.text
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/boot.h>
+
+.section ".text.head","ax",@progbits
+ .globl startup_32
+
+startup_32:
+ cld
+ cli
+ movl $(__BOOT_DS),%eax
+ movl %eax,%ds
+ movl %eax,%es
+ movl %eax,%fs
+ movl %eax,%gs
+ movl %eax,%ss
+
+/* Calculate the delta between where we were compiled to run
+ * at and where we were actually loaded at. This can only be done
+ * with a short local call on x86. Nothing else will tell us what
+ * address we are running at. The reserved chunk of the real-mode
+ * data at 0x1e4 (defined as a scratch field) are used as the stack
+ * for this calculation. Only 4 bytes are needed.
+ */
+ leal (0x1e4+4)(%esi), %esp
+ call 1f
+1: popl %ebp
+ subl $1b, %ebp
+
+/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ * contains the address where we should move the kernel image temporarily
+ * for safe in-place decompression.
+ */
+
+#ifdef CONFIG_RELOCATABLE
+ movl %ebp, %ebx
+ addl $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
+ andl $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
+#else
+ movl $LOAD_PHYSICAL_ADDR, %ebx
+#endif
+
+ /* Replace the compressed data size with the uncompressed size */
+ subl input_len(%ebp), %ebx
+ movl output_len(%ebp), %eax
+ addl %eax, %ebx
+ /* Add 8 bytes for every 32K input block */
+ shrl $12, %eax
+ addl %eax, %ebx
+ /* Add 32K + 18 bytes of extra slack */
+ addl $(32768 + 18), %ebx
+ /* Align on a 4K boundary */
+ addl $4095, %ebx
+ andl $~4095, %ebx
+
+/* Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+ pushl %esi
+ leal _end(%ebp), %esi
+ leal _end(%ebx), %edi
+ movl $(_end - startup_32), %ecx
+ std
+ rep
+ movsb
+ cld
+ popl %esi
+
+/* Compute the kernel start address.
+ */
+#ifdef CONFIG_RELOCATABLE
+ addl $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
+ andl $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
+#else
+ movl $LOAD_PHYSICAL_ADDR, %ebp
+#endif
+
+/*
+ * Jump to the relocated address.
+ */
+ leal relocated(%ebx), %eax
+ jmp *%eax
+.section ".text"
+relocated:
+
+/*
+ * Clear BSS
+ */
+ xorl %eax,%eax
+ leal _edata(%ebx),%edi
+ leal _end(%ebx), %ecx
+ subl %edi,%ecx
+ cld
+ rep
+ stosb
+
+/*
+ * Setup the stack for the decompressor
+ */
+ leal stack_end(%ebx), %esp
+
+/*
+ * Do the decompression, and jump to the new kernel..
+ */
+ movl output_len(%ebx), %eax
+ pushl %eax
+ pushl %ebp # output address
+ movl input_len(%ebx), %eax
+ pushl %eax # input_len
+ leal input_data(%ebx), %eax
+ pushl %eax # input_data
+ leal _end(%ebx), %eax
+ pushl %eax # end of the image as third argument
+ pushl %esi # real mode pointer as second arg
+ call decompress_kernel
+ addl $20, %esp
+ popl %ecx
+
+#if CONFIG_RELOCATABLE
+/* Find the address of the relocations.
+ */
+ movl %ebp, %edi
+ addl %ecx, %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 0(%edi), %ecx
+ testl %ecx, %ecx
+ jz 2f
+ addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
+ jmp 1b
+2:
+#endif
+
+/*
+ * Jump to the decompressed kernel.
+ */
+ xorl %ebx,%ebx
+ jmp *%ebp
+
+.bss
+.balign 4
+stack:
+ .fill 4096, 1, 0
+stack_end:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
new file mode 100644
index 000000000000..49467640751f
--- /dev/null
+++ b/arch/x86/boot/compressed/head_64.S
@@ -0,0 +1,311 @@
+/*
+ * linux/boot/head.S
+ *
+ * Copyright (C) 1991, 1992, 1993 Linus Torvalds
+ */
+
+/*
+ * head.S contains the 32-bit startup code.
+ *
+ * NOTE!!! Startup happens at absolute address 0x00001000, which is also where
+ * the page directory will exist. The startup code will be overwritten by
+ * the page directory. [According to comments etc elsewhere on a compressed
+ * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
+ *
+ * Page 0 is deliberately kept safe, since System Management Mode code in
+ * laptops may need to access the BIOS data stored there. This is also
+ * useful for future device drivers that either access the BIOS via VM86
+ * mode.
+ */
+
+/*
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+.code32
+.text
+
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/msr.h>
+
+.section ".text.head"
+ .code32
+ .globl startup_32
+
+startup_32:
+ cld
+ cli
+ movl $(__KERNEL_DS), %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %eax, %ss
+
+/* Calculate the delta between where we were compiled to run
+ * at and where we were actually loaded at. This can only be done
+ * with a short local call on x86. Nothing else will tell us what
+ * address we are running at. The reserved chunk of the real-mode
+ * data at 0x1e4 (defined as a scratch field) are used as the stack
+ * for this calculation. Only 4 bytes are needed.
+ */
+ leal (0x1e4+4)(%esi), %esp
+ call 1f
+1: popl %ebp
+ subl $1b, %ebp
+
+/* setup a stack and make sure cpu supports long mode. */
+ movl $user_stack_end, %eax
+ addl %ebp, %eax
+ movl %eax, %esp
+
+ call verify_cpu
+ testl %eax, %eax
+ jnz no_longmode
+
+/* Compute the delta between where we were compiled to run at
+ * and where the code will actually run at.
+ */
+/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ * contains the address where we should move the kernel image temporarily
+ * for safe in-place decompression.
+ */
+
+#ifdef CONFIG_RELOCATABLE
+ movl %ebp, %ebx
+ addl $(LARGE_PAGE_SIZE -1), %ebx
+ andl $LARGE_PAGE_MASK, %ebx
+#else
+ movl $CONFIG_PHYSICAL_START, %ebx
+#endif
+
+ /* Replace the compressed data size with the uncompressed size */
+ subl input_len(%ebp), %ebx
+ movl output_len(%ebp), %eax
+ addl %eax, %ebx
+ /* Add 8 bytes for every 32K input block */
+ shrl $12, %eax
+ addl %eax, %ebx
+ /* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
+ addl $(32768 + 18 + 4095), %ebx
+ andl $~4095, %ebx
+
+/*
+ * Prepare for entering 64 bit mode
+ */
+
+ /* Load new GDT with the 64bit segments using 32bit descriptor */
+ leal gdt(%ebp), %eax
+ movl %eax, gdt+2(%ebp)
+ lgdt gdt(%ebp)
+
+ /* Enable PAE mode */
+ xorl %eax, %eax
+ orl $(1 << 5), %eax
+ movl %eax, %cr4
+
+ /*
+ * Build early 4G boot pagetable
+ */
+ /* Initialize Page tables to 0*/
+ leal pgtable(%ebx), %edi
+ xorl %eax, %eax
+ movl $((4096*6)/4), %ecx
+ rep stosl
+
+ /* Build Level 4 */
+ leal pgtable + 0(%ebx), %edi
+ leal 0x1007 (%edi), %eax
+ movl %eax, 0(%edi)
+
+ /* Build Level 3 */
+ leal pgtable + 0x1000(%ebx), %edi
+ leal 0x1007(%edi), %eax
+ movl $4, %ecx
+1: movl %eax, 0x00(%edi)
+ addl $0x00001000, %eax
+ addl $8, %edi
+ decl %ecx
+ jnz 1b
+
+ /* Build Level 2 */
+ leal pgtable + 0x2000(%ebx), %edi
+ movl $0x00000183, %eax
+ movl $2048, %ecx
+1: movl %eax, 0(%edi)
+ addl $0x00200000, %eax
+ addl $8, %edi
+ decl %ecx
+ jnz 1b
+
+ /* Enable the boot page tables */
+ leal pgtable(%ebx), %eax
+ movl %eax, %cr3
+
+ /* Enable Long mode in EFER (Extended Feature Enable Register) */
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+
+ /* Setup for the jump to 64bit mode
+ *
+ * When the jump is performend we will be in long mode but
+ * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
+ * (and in turn EFER.LMA = 1). To jump into 64bit mode we use
+ * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+ * We place all of the values on our mini stack so lret can
+ * used to perform that far jump.
+ */
+ pushl $__KERNEL_CS
+ leal startup_64(%ebp), %eax
+ pushl %eax
+
+ /* Enter paged protected Mode, activating Long Mode */
+ movl $0x80000001, %eax /* Enable Paging and Protected mode */
+ movl %eax, %cr0
+
+ /* Jump from 32bit compatibility mode into 64bit mode. */
+ lret
+
+no_longmode:
+ /* This isn't an x86-64 CPU so hang */
+1:
+ hlt
+ jmp 1b
+
+#include "../../kernel/verify_cpu_64.S"
+
+ /* 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)
+ /* 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.
+ */
+
+ /* Setup data segments. */
+ xorl %eax, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ 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
+ * we were loaded at aligned to a 2M boundary. %rbp contains the
+ * decompressed kernel start address.
+ *
+ * If it is a relocatable kernel then decompress and run the kernel
+ * from load address aligned to 2MB addr, otherwise decompress and
+ * run the kernel from CONFIG_PHYSICAL_START
+ */
+
+ /* Start with the delta to where the kernel will run at. */
+#ifdef CONFIG_RELOCATABLE
+ leaq startup_32(%rip) /* - $startup_32 */, %rbp
+ addq $(LARGE_PAGE_SIZE - 1), %rbp
+ andq $LARGE_PAGE_MASK, %rbp
+ movq %rbp, %rbx
+#else
+ movq $CONFIG_PHYSICAL_START, %rbp
+ movq %rbp, %rbx
+#endif
+
+ /* Replace the compressed data size with the uncompressed size */
+ movl input_len(%rip), %eax
+ subq %rax, %rbx
+ movl output_len(%rip), %eax
+ addq %rax, %rbx
+ /* Add 8 bytes for every 32K input block */
+ shrq $12, %rax
+ addq %rax, %rbx
+ /* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
+ addq $(32768 + 18 + 4095), %rbx
+ andq $~4095, %rbx
+
+/* Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+ leaq _end(%rip), %r8
+ leaq _end(%rbx), %r9
+ movq $_end /* - $startup_32 */, %rcx
+1: subq $8, %r8
+ subq $8, %r9
+ movq 0(%r8), %rax
+ movq %rax, 0(%r9)
+ subq $8, %rcx
+ jnz 1b
+
+/*
+ * Jump to the relocated address.
+ */
+ leaq relocated(%rbx), %rax
+ jmp *%rax
+
+.section ".text"
+relocated:
+
+/*
+ * Clear BSS
+ */
+ xorq %rax, %rax
+ leaq _edata(%rbx), %rdi
+ leaq _end(%rbx), %rcx
+ subq %rdi, %rcx
+ cld
+ rep
+ stosb
+
+ /* Setup the stack */
+ leaq user_stack_end(%rip), %rsp
+
+ /* zero EFLAGS after setting rsp */
+ pushq $0
+ popfq
+
+/*
+ * Do the decompression, and jump to the new kernel..
+ */
+ pushq %rsi # Save the real mode argument
+ movq %rsi, %rdi # real mode address
+ leaq _heap(%rip), %rsi # _heap
+ leaq input_data(%rip), %rdx # input_data
+ movl input_len(%rip), %eax
+ movq %rax, %rcx # input_len
+ movq %rbp, %r8 # output
+ call decompress_kernel
+ popq %rsi
+
+
+/*
+ * Jump to the decompressed kernel.
+ */
+ jmp *%rbp
+
+ .data
+gdt:
+ .word gdt_end - gdt
+ .long gdt
+ .word 0
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x00af9a000000ffff /* __KERNEL_CS */
+ .quad 0x00cf92000000ffff /* __KERNEL_DS */
+ .quad 0x0080890000000000 /* TS descriptor */
+ .quad 0x0000000000000000 /* TS continued */
+gdt_end:
+ .bss
+/* Stack for uncompression */
+ .balign 4
+user_stack:
+ .fill 4096,4,0
+user_stack_end:
diff --git a/arch/x86/boot/compressed/misc_32.c b/arch/x86/boot/compressed/misc_32.c
new file mode 100644
index 000000000000..b28505c544c9
--- /dev/null
+++ b/arch/x86/boot/compressed/misc_32.c
@@ -0,0 +1,379 @@
+/*
+ * misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ * puts by Nick Holloway 1993, better puts by Martin Mares 1995
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+
+#undef CONFIG_PARAVIRT
+#include <linux/linkage.h>
+#include <linux/vmalloc.h>
+#include <linux/screen_info.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/boot.h>
+
+/* WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically
+ * at run time, but no relocation processing is performed.
+ * This means that it is not safe to place pointers in static structures.
+ */
+
+/*
+ * Getting to provable safe in place decompression is hard.
+ * Worst case behaviours need to be analized.
+ * Background information:
+ *
+ * The file layout is:
+ * magic[2]
+ * method[1]
+ * flags[1]
+ * timestamp[4]
+ * extraflags[1]
+ * os[1]
+ * compressed data blocks[N]
+ * crc[4] orig_len[4]
+ *
+ * resulting in 18 bytes of non compressed data overhead.
+ *
+ * Files divided into blocks
+ * 1 bit (last block flag)
+ * 2 bits (block type)
+ *
+ * 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved.
+ * The smallest block type encoding is always used.
+ *
+ * stored:
+ * 32 bits length in bytes.
+ *
+ * fixed:
+ * magic fixed tree.
+ * symbols.
+ *
+ * dynamic:
+ * dynamic tree encoding.
+ * symbols.
+ *
+ *
+ * The buffer for decompression in place is the length of the
+ * uncompressed data, plus a small amount extra to keep the algorithm safe.
+ * The compressed data is placed at the end of the buffer. The output
+ * pointer is placed at the start of the buffer and the input pointer
+ * is placed where the compressed data starts. Problems will occur
+ * when the output pointer overruns the input pointer.
+ *
+ * The output pointer can only overrun the input pointer if the input
+ * pointer is moving faster than the output pointer. A condition only
+ * triggered by data whose compressed form is larger than the uncompressed
+ * form.
+ *
+ * The worst case at the block level is a growth of the compressed data
+ * of 5 bytes per 32767 bytes.
+ *
+ * The worst case internal to a compressed block is very hard to figure.
+ * The worst case can at least be boundined by having one bit that represents
+ * 32764 bytes and then all of the rest of the bytes representing the very
+ * very last byte.
+ *
+ * All of which is enough to compute an amount of extra data that is required
+ * to be safe. To avoid problems at the block level allocating 5 extra bytes
+ * per 32767 bytes of data is sufficient. To avoind problems internal to a block
+ * adding an extra 32767 bytes (the worst case uncompressed block size) is
+ * sufficient, to ensure that in the worst case the decompressed data for
+ * block will stop the byte before the compressed data for a block begins.
+ * To avoid problems with the compressed data's meta information an extra 18
+ * bytes are needed. Leading to the formula:
+ *
+ * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
+ *
+ * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+ * Adding 32768 instead of 32767 just makes for round numbers.
+ * Adding the decompressor_size is necessary as it musht live after all
+ * of the data as well. Last I measured the decompressor is about 14K.
+ * 10K of actuall data and 4K of bss.
+ *
+ */
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args) args
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#define memzero(s, n) memset ((s), 0, (n))
+
+typedef unsigned char uch;
+typedef unsigned short ush;
+typedef unsigned long ulg;
+
+#define WSIZE 0x80000000 /* Window size must be at least 32k,
+ * and a power of two
+ * We don't actually have a window just
+ * a huge output buffer so I report
+ * a 2G windows size, as that should
+ * always be larger than our output buffer.
+ */
+
+static uch *inbuf; /* input buffer */
+static uch *window; /* Sliding window buffer, (and final output buffer) */
+
+static unsigned insize; /* valid bytes in inbuf */
+static unsigned inptr; /* index of next byte to be processed in inbuf */
+static unsigned outcnt; /* bytes in output buffer */
+
+/* gzip flag byte */
+#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */
+#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
+#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */
+#define ORIG_NAME 0x08 /* bit 3 set: original file name present */
+#define COMMENT 0x10 /* bit 4 set: file comment present */
+#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */
+#define RESERVED 0xC0 /* bit 6,7: reserved */
+
+#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions */
+#ifdef DEBUG
+# define Assert(cond,msg) {if(!(cond)) error(msg);}
+# define Trace(x) fprintf x
+# define Tracev(x) {if (verbose) fprintf x ;}
+# define Tracevv(x) {if (verbose>1) fprintf x ;}
+# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+# define Assert(cond,msg)
+# define Trace(x)
+# define Tracev(x)
+# define Tracevv(x)
+# define Tracec(c,x)
+# define Tracecv(c,x)
+#endif
+
+static int fill_inbuf(void);
+static void flush_window(void);
+static void error(char *m);
+static void gzip_mark(void **);
+static void gzip_release(void **);
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+static unsigned char *real_mode; /* Pointer to real-mode data */
+
+#define RM_EXT_MEM_K (*(unsigned short *)(real_mode + 0x2))
+#ifndef STANDARD_MEMORY_BIOS_CALL
+#define RM_ALT_MEM_K (*(unsigned long *)(real_mode + 0x1e0))
+#endif
+#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
+
+extern unsigned char input_data[];
+extern int input_len;
+
+static long bytes_out = 0;
+
+static void *malloc(int size);
+static void free(void *where);
+
+static void *memset(void *s, int c, unsigned n);
+static void *memcpy(void *dest, const void *src, unsigned n);
+
+static void putstr(const char *);
+
+static unsigned long free_mem_ptr;
+static unsigned long free_mem_end_ptr;
+
+#define HEAP_SIZE 0x4000
+
+static char *vidmem = (char *)0xb8000;
+static int vidport;
+static int lines, cols;
+
+#ifdef CONFIG_X86_NUMAQ
+void *xquad_portio;
+#endif
+
+#include "../../../../lib/inflate.c"
+
+static void *malloc(int size)
+{
+ void *p;
+
+ if (size <0) error("Malloc error");
+ if (free_mem_ptr <= 0) error("Memory error");
+
+ free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */
+
+ p = (void *)free_mem_ptr;
+ free_mem_ptr += size;
+
+ if (free_mem_ptr >= free_mem_end_ptr)
+ error("Out of memory");
+
+ return p;
+}
+
+static void free(void *where)
+{ /* Don't care */
+}
+
+static void gzip_mark(void **ptr)
+{
+ *ptr = (void *) free_mem_ptr;
+}
+
+static void gzip_release(void **ptr)
+{
+ free_mem_ptr = (unsigned long) *ptr;
+}
+
+static void scroll(void)
+{
+ int i;
+
+ memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 );
+ for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 )
+ vidmem[i] = ' ';
+}
+
+static void putstr(const char *s)
+{
+ int x,y,pos;
+ char c;
+
+ x = RM_SCREEN_INFO.orig_x;
+ y = RM_SCREEN_INFO.orig_y;
+
+ while ( ( c = *s++ ) != '\0' ) {
+ if ( c == '\n' ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ } else {
+ vidmem [ ( x + cols * y ) * 2 ] = c;
+ if ( ++x >= cols ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ }
+ }
+ }
+
+ RM_SCREEN_INFO.orig_x = x;
+ RM_SCREEN_INFO.orig_y = y;
+
+ pos = (x + cols * y) * 2; /* Update cursor position */
+ outb_p(14, vidport);
+ outb_p(0xff & (pos >> 9), vidport+1);
+ outb_p(15, vidport);
+ outb_p(0xff & (pos >> 1), vidport+1);
+}
+
+static void* memset(void* s, int c, unsigned n)
+{
+ int i;
+ char *ss = (char*)s;
+
+ for (i=0;i<n;i++) ss[i] = c;
+ return s;
+}
+
+static void* memcpy(void* dest, const void* src, unsigned n)
+{
+ int i;
+ char *d = (char *)dest, *s = (char *)src;
+
+ for (i=0;i<n;i++) d[i] = s[i];
+ return dest;
+}
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+static int fill_inbuf(void)
+{
+ error("ran out of input data");
+ return 0;
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+static void flush_window(void)
+{
+ /* With my window equal to my output buffer
+ * I only need to compute the crc here.
+ */
+ ulg c = crc; /* temporary variable */
+ unsigned n;
+ uch *in, ch;
+
+ in = window;
+ for (n = 0; n < outcnt; n++) {
+ ch = *in++;
+ c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+ }
+ crc = c;
+ bytes_out += (ulg)outcnt;
+ outcnt = 0;
+}
+
+static void error(char *x)
+{
+ putstr("\n\n");
+ putstr(x);
+ putstr("\n\n -- System halted");
+
+ while(1); /* Halt */
+}
+
+asmlinkage void decompress_kernel(void *rmode, unsigned long end,
+ uch *input_data, unsigned long input_len, uch *output)
+{
+ real_mode = rmode;
+
+ if (RM_SCREEN_INFO.orig_video_mode == 7) {
+ vidmem = (char *) 0xb0000;
+ vidport = 0x3b4;
+ } else {
+ vidmem = (char *) 0xb8000;
+ vidport = 0x3d4;
+ }
+
+ lines = RM_SCREEN_INFO.orig_video_lines;
+ cols = RM_SCREEN_INFO.orig_video_cols;
+
+ window = output; /* Output buffer (Normally at 1M) */
+ free_mem_ptr = end; /* Heap */
+ free_mem_end_ptr = end + HEAP_SIZE;
+ inbuf = input_data; /* Input buffer */
+ insize = input_len;
+ inptr = 0;
+
+ if ((u32)output & (CONFIG_PHYSICAL_ALIGN -1))
+ error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
+ if (end > ((-__PAGE_OFFSET-(512 <<20)-1) & 0x7fffffff))
+ error("Destination address too large");
+#ifndef CONFIG_RELOCATABLE
+ if ((u32)output != LOAD_PHYSICAL_ADDR)
+ error("Wrong destination address");
+#endif
+
+ makecrc();
+ putstr("Uncompressing Linux... ");
+ gunzip();
+ putstr("Ok, booting the kernel.\n");
+ return;
+}
diff --git a/arch/x86/boot/compressed/misc_64.c b/arch/x86/boot/compressed/misc_64.c
new file mode 100644
index 000000000000..f932b0e89096
--- /dev/null
+++ b/arch/x86/boot/compressed/misc_64.c
@@ -0,0 +1,371 @@
+/*
+ * misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ * puts by Nick Holloway 1993, better puts by Martin Mares 1995
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+
+#define _LINUX_STRING_H_ 1
+#define __LINUX_BITMAP_H 1
+
+#include <linux/linkage.h>
+#include <linux/screen_info.h>
+#include <asm/io.h>
+#include <asm/page.h>
+
+/* WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically
+ * at run time, but no relocation processing is performed.
+ * This means that it is not safe to place pointers in static structures.
+ */
+
+/*
+ * Getting to provable safe in place decompression is hard.
+ * Worst case behaviours need to be analized.
+ * Background information:
+ *
+ * The file layout is:
+ * magic[2]
+ * method[1]
+ * flags[1]
+ * timestamp[4]
+ * extraflags[1]
+ * os[1]
+ * compressed data blocks[N]
+ * crc[4] orig_len[4]
+ *
+ * resulting in 18 bytes of non compressed data overhead.
+ *
+ * Files divided into blocks
+ * 1 bit (last block flag)
+ * 2 bits (block type)
+ *
+ * 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved.
+ * The smallest block type encoding is always used.
+ *
+ * stored:
+ * 32 bits length in bytes.
+ *
+ * fixed:
+ * magic fixed tree.
+ * symbols.
+ *
+ * dynamic:
+ * dynamic tree encoding.
+ * symbols.
+ *
+ *
+ * The buffer for decompression in place is the length of the
+ * uncompressed data, plus a small amount extra to keep the algorithm safe.
+ * The compressed data is placed at the end of the buffer. The output
+ * pointer is placed at the start of the buffer and the input pointer
+ * is placed where the compressed data starts. Problems will occur
+ * when the output pointer overruns the input pointer.
+ *
+ * The output pointer can only overrun the input pointer if the input
+ * pointer is moving faster than the output pointer. A condition only
+ * triggered by data whose compressed form is larger than the uncompressed
+ * form.
+ *
+ * The worst case at the block level is a growth of the compressed data
+ * of 5 bytes per 32767 bytes.
+ *
+ * The worst case internal to a compressed block is very hard to figure.
+ * The worst case can at least be boundined by having one bit that represents
+ * 32764 bytes and then all of the rest of the bytes representing the very
+ * very last byte.
+ *
+ * All of which is enough to compute an amount of extra data that is required
+ * to be safe. To avoid problems at the block level allocating 5 extra bytes
+ * per 32767 bytes of data is sufficient. To avoind problems internal to a block
+ * adding an extra 32767 bytes (the worst case uncompressed block size) is
+ * sufficient, to ensure that in the worst case the decompressed data for
+ * block will stop the byte before the compressed data for a block begins.
+ * To avoid problems with the compressed data's meta information an extra 18
+ * bytes are needed. Leading to the formula:
+ *
+ * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
+ *
+ * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+ * Adding 32768 instead of 32767 just makes for round numbers.
+ * Adding the decompressor_size is necessary as it musht live after all
+ * of the data as well. Last I measured the decompressor is about 14K.
+ * 10K of actuall data and 4K of bss.
+ *
+ */
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args) args
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#define memzero(s, n) memset ((s), 0, (n))
+
+typedef unsigned char uch;
+typedef unsigned short ush;
+typedef unsigned long ulg;
+
+#define WSIZE 0x80000000 /* Window size must be at least 32k,
+ * and a power of two
+ * We don't actually have a window just
+ * a huge output buffer so I report
+ * a 2G windows size, as that should
+ * always be larger than our output buffer.
+ */
+
+static uch *inbuf; /* input buffer */
+static uch *window; /* Sliding window buffer, (and final output buffer) */
+
+static unsigned insize; /* valid bytes in inbuf */
+static unsigned inptr; /* index of next byte to be processed in inbuf */
+static unsigned outcnt; /* bytes in output buffer */
+
+/* gzip flag byte */
+#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */
+#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
+#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */
+#define ORIG_NAME 0x08 /* bit 3 set: original file name present */
+#define COMMENT 0x10 /* bit 4 set: file comment present */
+#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */
+#define RESERVED 0xC0 /* bit 6,7: reserved */
+
+#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
+
+/* Diagnostic functions */
+#ifdef DEBUG
+# define Assert(cond,msg) {if(!(cond)) error(msg);}
+# define Trace(x) fprintf x
+# define Tracev(x) {if (verbose) fprintf x ;}
+# define Tracevv(x) {if (verbose>1) fprintf x ;}
+# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+# define Assert(cond,msg)
+# define Trace(x)
+# define Tracev(x)
+# define Tracevv(x)
+# define Tracec(c,x)
+# define Tracecv(c,x)
+#endif
+
+static int fill_inbuf(void);
+static void flush_window(void);
+static void error(char *m);
+static void gzip_mark(void **);
+static void gzip_release(void **);
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+static unsigned char *real_mode; /* Pointer to real-mode data */
+
+#define RM_EXT_MEM_K (*(unsigned short *)(real_mode + 0x2))
+#ifndef STANDARD_MEMORY_BIOS_CALL
+#define RM_ALT_MEM_K (*(unsigned long *)(real_mode + 0x1e0))
+#endif
+#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
+
+extern unsigned char input_data[];
+extern int input_len;
+
+static long bytes_out = 0;
+
+static void *malloc(int size);
+static void free(void *where);
+
+static void *memset(void *s, int c, unsigned n);
+static void *memcpy(void *dest, const void *src, unsigned n);
+
+static void putstr(const char *);
+
+static long free_mem_ptr;
+static long free_mem_end_ptr;
+
+#define HEAP_SIZE 0x7000
+
+static char *vidmem = (char *)0xb8000;
+static int vidport;
+static int lines, cols;
+
+#include "../../../../lib/inflate.c"
+
+static void *malloc(int size)
+{
+ void *p;
+
+ if (size <0) error("Malloc error");
+ if (free_mem_ptr <= 0) error("Memory error");
+
+ free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */
+
+ p = (void *)free_mem_ptr;
+ free_mem_ptr += size;
+
+ if (free_mem_ptr >= free_mem_end_ptr)
+ error("Out of memory");
+
+ return p;
+}
+
+static void free(void *where)
+{ /* Don't care */
+}
+
+static void gzip_mark(void **ptr)
+{
+ *ptr = (void *) free_mem_ptr;
+}
+
+static void gzip_release(void **ptr)
+{
+ free_mem_ptr = (long) *ptr;
+}
+
+static void scroll(void)
+{
+ int i;
+
+ memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 );
+ for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 )
+ vidmem[i] = ' ';
+}
+
+static void putstr(const char *s)
+{
+ int x,y,pos;
+ char c;
+
+ x = RM_SCREEN_INFO.orig_x;
+ y = RM_SCREEN_INFO.orig_y;
+
+ while ( ( c = *s++ ) != '\0' ) {
+ if ( c == '\n' ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ } else {
+ vidmem [ ( x + cols * y ) * 2 ] = c;
+ if ( ++x >= cols ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ scroll();
+ y--;
+ }
+ }
+ }
+ }
+
+ RM_SCREEN_INFO.orig_x = x;
+ RM_SCREEN_INFO.orig_y = y;
+
+ pos = (x + cols * y) * 2; /* Update cursor position */
+ outb_p(14, vidport);
+ outb_p(0xff & (pos >> 9), vidport+1);
+ outb_p(15, vidport);
+ outb_p(0xff & (pos >> 1), vidport+1);
+}
+
+static void* memset(void* s, int c, unsigned n)
+{
+ int i;
+ char *ss = (char*)s;
+
+ for (i=0;i<n;i++) ss[i] = c;
+ return s;
+}
+
+static void* memcpy(void* dest, const void* src, unsigned n)
+{
+ int i;
+ char *d = (char *)dest, *s = (char *)src;
+
+ for (i=0;i<n;i++) d[i] = s[i];
+ return dest;
+}
+
+/* ===========================================================================
+ * Fill the input buffer. This is called only when the buffer is empty
+ * and at least one byte is really needed.
+ */
+static int fill_inbuf(void)
+{
+ error("ran out of input data");
+ return 0;
+}
+
+/* ===========================================================================
+ * Write the output window window[0..outcnt-1] and update crc and bytes_out.
+ * (Used for the decompressed data only.)
+ */
+static void flush_window(void)
+{
+ /* With my window equal to my output buffer
+ * I only need to compute the crc here.
+ */
+ ulg c = crc; /* temporary variable */
+ unsigned n;
+ uch *in, ch;
+
+ in = window;
+ for (n = 0; n < outcnt; n++) {
+ ch = *in++;
+ c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
+ }
+ crc = c;
+ bytes_out += (ulg)outcnt;
+ outcnt = 0;
+}
+
+static void error(char *x)
+{
+ putstr("\n\n");
+ putstr(x);
+ putstr("\n\n -- System halted");
+
+ while(1); /* Halt */
+}
+
+asmlinkage void decompress_kernel(void *rmode, unsigned long heap,
+ uch *input_data, unsigned long input_len, uch *output)
+{
+ real_mode = rmode;
+
+ if (RM_SCREEN_INFO.orig_video_mode == 7) {
+ vidmem = (char *) 0xb0000;
+ vidport = 0x3b4;
+ } else {
+ vidmem = (char *) 0xb8000;
+ vidport = 0x3d4;
+ }
+
+ lines = RM_SCREEN_INFO.orig_video_lines;
+ cols = RM_SCREEN_INFO.orig_video_cols;
+
+ window = output; /* Output buffer (Normally at 1M) */
+ free_mem_ptr = heap; /* Heap */
+ free_mem_end_ptr = heap + HEAP_SIZE;
+ inbuf = input_data; /* Input buffer */
+ insize = input_len;
+ inptr = 0;
+
+ if ((ulg)output & (__KERNEL_ALIGN - 1))
+ error("Destination address not 2M aligned");
+ if ((ulg)output >= 0xffffffffffUL)
+ error("Destination address too large");
+
+ makecrc();
+ putstr(".\nDecompressing Linux...");
+ gunzip();
+ putstr("done.\nBooting the kernel.\n");
+ return;
+}
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
new file mode 100644
index 000000000000..2d77ee728f92
--- /dev/null
+++ b/arch/x86/boot/compressed/relocs.c
@@ -0,0 +1,631 @@
+#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>
+
+#define MAX_SHDRS 100
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+static Elf32_Ehdr ehdr;
+static Elf32_Shdr shdr[MAX_SHDRS];
+static Elf32_Sym *symtab[MAX_SHDRS];
+static Elf32_Rel *reltab[MAX_SHDRS];
+static char *strtab[MAX_SHDRS];
+static unsigned long reloc_count, reloc_idx;
+static unsigned long *relocs;
+
+/*
+ * 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* safe_abs_relocs[] = {
+ "__kernel_vsyscall",
+ "__kernel_rt_sigreturn",
+ "__kernel_sigreturn",
+ "SYSENTER_RETURN",
+ "VDSO_NOTE_MASK",
+ "xen_irq_disable_direct_reloc",
+ "xen_save_fl_direct_reloc",
+};
+
+static int is_safe_abs_reloc(const char* sym_name)
+{
+ int i, array_size;
+
+ array_size = sizeof(safe_abs_relocs)/sizeof(char*);
+
+ for(i = 0; i < array_size; i++) {
+ if (!strcmp(sym_name, safe_abs_relocs[i]))
+ /* Match found */
+ return 1;
+ }
+ if (strncmp(sym_name, "__crc_", 6) == 0)
+ return 1;
+ return 0;
+}
+
+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)) {
+ name = type_name[type];
+ }
+ return name;
+}
+
+static const char *sec_name(unsigned shndx)
+{
+ const char *sec_strtab;
+ const char *name;
+ sec_strtab = strtab[ehdr.e_shstrndx];
+ name = "<noname>";
+ if (shndx < ehdr.e_shnum) {
+ name = sec_strtab + shdr[shndx].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(shdr[sym->st_shndx].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, 4) != 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;
+ if (ehdr.e_shnum > MAX_SHDRS) {
+ die("%d section headers supported: %d\n",
+ ehdr.e_shnum, MAX_SHDRS);
+ }
+ if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
+ die("Seek to %d failed: %s\n",
+ ehdr.e_shoff, strerror(errno));
+ }
+ if (fread(&shdr, sizeof(shdr[0]), ehdr.e_shnum, fp) != ehdr.e_shnum) {
+ die("Cannot read ELF section headers: %s\n",
+ strerror(errno));
+ }
+ for(i = 0; i < ehdr.e_shnum; i++) {
+ shdr[i].sh_name = elf32_to_cpu(shdr[i].sh_name);
+ shdr[i].sh_type = elf32_to_cpu(shdr[i].sh_type);
+ shdr[i].sh_flags = elf32_to_cpu(shdr[i].sh_flags);
+ shdr[i].sh_addr = elf32_to_cpu(shdr[i].sh_addr);
+ shdr[i].sh_offset = elf32_to_cpu(shdr[i].sh_offset);
+ shdr[i].sh_size = elf32_to_cpu(shdr[i].sh_size);
+ shdr[i].sh_link = elf32_to_cpu(shdr[i].sh_link);
+ shdr[i].sh_info = elf32_to_cpu(shdr[i].sh_info);
+ shdr[i].sh_addralign = elf32_to_cpu(shdr[i].sh_addralign);
+ shdr[i].sh_entsize = elf32_to_cpu(shdr[i].sh_entsize);
+ }
+
+}
+
+static void read_strtabs(FILE *fp)
+{
+ int i;
+ for(i = 0; i < ehdr.e_shnum; i++) {
+ if (shdr[i].sh_type != SHT_STRTAB) {
+ continue;
+ }
+ strtab[i] = malloc(shdr[i].sh_size);
+ if (!strtab[i]) {
+ die("malloc of %d bytes for strtab failed\n",
+ shdr[i].sh_size);
+ }
+ if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+ die("Seek to %d failed: %s\n",
+ shdr[i].sh_offset, strerror(errno));
+ }
+ if (fread(strtab[i], 1, shdr[i].sh_size, fp) != shdr[i].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++) {
+ if (shdr[i].sh_type != SHT_SYMTAB) {
+ continue;
+ }
+ symtab[i] = malloc(shdr[i].sh_size);
+ if (!symtab[i]) {
+ die("malloc of %d bytes for symtab failed\n",
+ shdr[i].sh_size);
+ }
+ if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+ die("Seek to %d failed: %s\n",
+ shdr[i].sh_offset, strerror(errno));
+ }
+ if (fread(symtab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) {
+ die("Cannot read symbol table: %s\n",
+ strerror(errno));
+ }
+ for(j = 0; j < shdr[i].sh_size/sizeof(symtab[i][0]); j++) {
+ symtab[i][j].st_name = elf32_to_cpu(symtab[i][j].st_name);
+ symtab[i][j].st_value = elf32_to_cpu(symtab[i][j].st_value);
+ symtab[i][j].st_size = elf32_to_cpu(symtab[i][j].st_size);
+ symtab[i][j].st_shndx = elf16_to_cpu(symtab[i][j].st_shndx);
+ }
+ }
+}
+
+
+static void read_relocs(FILE *fp)
+{
+ int i,j;
+ for(i = 0; i < ehdr.e_shnum; i++) {
+ if (shdr[i].sh_type != SHT_REL) {
+ continue;
+ }
+ reltab[i] = malloc(shdr[i].sh_size);
+ if (!reltab[i]) {
+ die("malloc of %d bytes for relocs failed\n",
+ shdr[i].sh_size);
+ }
+ if (fseek(fp, shdr[i].sh_offset, SEEK_SET) < 0) {
+ die("Seek to %d failed: %s\n",
+ shdr[i].sh_offset, strerror(errno));
+ }
+ if (fread(reltab[i], 1, shdr[i].sh_size, fp) != shdr[i].sh_size) {
+ die("Cannot read symbol table: %s\n",
+ strerror(errno));
+ }
+ for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
+ reltab[i][j].r_offset = elf32_to_cpu(reltab[i][j].r_offset);
+ reltab[i][j].r_info = elf32_to_cpu(reltab[i][j].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++) {
+ char *sym_strtab;
+ Elf32_Sym *sh_symtab;
+ int j;
+ if (shdr[i].sh_type != SHT_SYMTAB) {
+ continue;
+ }
+ sh_symtab = symtab[i];
+ sym_strtab = strtab[shdr[i].sh_link];
+ for(j = 0; j < shdr[i].sh_size/sizeof(symtab[0][0]); j++) {
+ Elf32_Sym *sym;
+ const char *name;
+ sym = &symtab[i][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++) {
+ char *sym_strtab;
+ Elf32_Sym *sh_symtab;
+ unsigned sec_applies, sec_symtab;
+ int j;
+ if (shdr[i].sh_type != SHT_REL) {
+ continue;
+ }
+ sec_symtab = shdr[i].sh_link;
+ sec_applies = shdr[i].sh_info;
+ if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) {
+ continue;
+ }
+ sh_symtab = symtab[sec_symtab];
+ sym_strtab = strtab[shdr[sec_symtab].sh_link];
+ for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
+ Elf32_Rel *rel;
+ Elf32_Sym *sym;
+ const char *name;
+ rel = &reltab[i][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_safe_abs_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;
+ unsigned sec_applies, sec_symtab;
+ int j;
+ if (shdr[i].sh_type != SHT_REL) {
+ continue;
+ }
+ sec_symtab = shdr[i].sh_link;
+ sec_applies = shdr[i].sh_info;
+ if (!(shdr[sec_applies].sh_flags & SHF_ALLOC)) {
+ continue;
+ }
+ sh_symtab = symtab[sec_symtab];
+ sym_strtab = strtab[shdr[sec_symtab].sh_link];
+ for(j = 0; j < shdr[i].sh_size/sizeof(reltab[0][0]); j++) {
+ Elf32_Rel *rel;
+ Elf32_Sym *sym;
+ unsigned r_type;
+ rel = &reltab[i][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) {
+ continue;
+ }
+ if (r_type == R_386_PC32) {
+ /* PC relative relocations don't need to be adjusted */
+ }
+ else if (r_type == R_386_32) {
+ /* Visit relocations that need to be adjusted */
+ visit(rel, sym);
+ }
+ else {
+ die("Unsupported relocation type: %d\n", r_type);
+ }
+ }
+ }
+}
+
+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];
+ buf[0] = buf[1] = buf[2] = buf[3] = 0;
+ /* Print a stop */
+ printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]);
+ /* 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;
+ printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]);
+ }
+ }
+}
+
+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;
+
+ 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/vmlinux_32.lds b/arch/x86/boot/compressed/vmlinux_32.lds
new file mode 100644
index 000000000000..cc4854f6c6c1
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_32.lds
@@ -0,0 +1,43 @@
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(startup_32)
+SECTIONS
+{
+ /* Be careful parts of head.S assume startup_32 is at
+ * address 0.
+ */
+ . = 0 ;
+ .text.head : {
+ _head = . ;
+ *(.text.head)
+ _ehead = . ;
+ }
+ .data.compressed : {
+ *(.data.compressed)
+ }
+ .text : {
+ _text = .; /* Text */
+ *(.text)
+ *(.text.*)
+ _etext = . ;
+ }
+ .rodata : {
+ _rodata = . ;
+ *(.rodata) /* read-only data */
+ *(.rodata.*)
+ _erodata = . ;
+ }
+ .data : {
+ _data = . ;
+ *(.data)
+ *(.data.*)
+ _edata = . ;
+ }
+ .bss : {
+ _bss = . ;
+ *(.bss)
+ *(.bss.*)
+ *(COMMON)
+ _end = . ;
+ }
+}
diff --git a/arch/x86/boot/compressed/vmlinux_32.scr b/arch/x86/boot/compressed/vmlinux_32.scr
new file mode 100644
index 000000000000..707a88f7f29e
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_32.scr
@@ -0,0 +1,10 @@
+SECTIONS
+{
+ .data.compressed : {
+ input_len = .;
+ LONG(input_data_end - input_data) input_data = .;
+ *(.data)
+ output_len = . - 4;
+ input_data_end = .;
+ }
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.lds b/arch/x86/boot/compressed/vmlinux_64.lds
new file mode 100644
index 000000000000..94c13e557fb4
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_64.lds
@@ -0,0 +1,44 @@
+OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(startup_64)
+SECTIONS
+{
+ /* Be careful parts of head.S assume startup_32 is at
+ * address 0.
+ */
+ . = 0;
+ .text : {
+ _head = . ;
+ *(.text.head)
+ _ehead = . ;
+ *(.text.compressed)
+ _text = .; /* Text */
+ *(.text)
+ *(.text.*)
+ _etext = . ;
+ }
+ .rodata : {
+ _rodata = . ;
+ *(.rodata) /* read-only data */
+ *(.rodata.*)
+ _erodata = . ;
+ }
+ .data : {
+ _data = . ;
+ *(.data)
+ *(.data.*)
+ _edata = . ;
+ }
+ .bss : {
+ _bss = . ;
+ *(.bss)
+ *(.bss.*)
+ *(COMMON)
+ . = ALIGN(8);
+ _end = . ;
+ . = ALIGN(4096);
+ pgtable = . ;
+ . = . + 4096 * 6;
+ _heap = .;
+ }
+}
diff --git a/arch/x86/boot/compressed/vmlinux_64.scr b/arch/x86/boot/compressed/vmlinux_64.scr
new file mode 100644
index 000000000000..bd1429ce193e
--- /dev/null
+++ b/arch/x86/boot/compressed/vmlinux_64.scr
@@ -0,0 +1,10 @@
+SECTIONS
+{
+ .text.compressed : {
+ input_len = .;
+ LONG(input_data_end - input_data) input_data = .;
+ *(.data)
+ output_len = . - 4;
+ input_data_end = .;
+ }
+}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.