diff options
Diffstat (limited to 'arch/x86/boot/compressed/head_64.S')
| -rw-r--r-- | arch/x86/boot/compressed/head_64.S | 747 |
1 files changed, 747 insertions, 0 deletions
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S new file mode 100644 index 000000000..03c4328a8 --- /dev/null +++ b/arch/x86/boot/compressed/head_64.S @@ -0,0 +1,747 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * 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/init.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/boot.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> +#include <asm/asm-offsets.h> +#include <asm/bootparam.h> +#include <asm/desc_defs.h> +#include <asm/trapnr.h> +#include "pgtable.h" + +/* + * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result + * in assembly errors due to trying to move .org backward due to the excessive + * alignment. + */ +#undef __ALIGN +#define __ALIGN .balign 16, 0x90 + +/* + * Locally defined symbols should be marked hidden: + */ + .hidden _bss + .hidden _ebss + .hidden _end + + __HEAD + +/* + * This macro gives the relative virtual address of X, i.e. the offset of X + * from startup_32. This is the same as the link-time virtual address of X, + * since startup_32 is at 0, but defining it this way tells the + * assembler/linker that we do not want the actual run-time address of X. This + * prevents the linker from trying to create unwanted run-time relocation + * entries for the reference when the compressed kernel is linked as PIE. + * + * A reference X(%reg) will result in the link-time VA of X being stored with + * the instruction, and a run-time R_X86_64_RELATIVE relocation entry that + * adds the 64-bit base address where the kernel is loaded. + * + * Replacing it with (X-startup_32)(%reg) results in the offset being stored, + * and no run-time relocation. + * + * The macro should be used as a displacement with a base register containing + * the run-time address of startup_32 [i.e. rva(X)(%reg)], or as an immediate + * [$ rva(X)]. + * + * This macro can only be used from within the .head.text section, since the + * expression requires startup_32 to be in the same section as the code being + * assembled. + */ +#define rva(X) ((X) - startup_32) + + .code32 +SYM_FUNC_START(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 + cli + +/* + * 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 (BP_scratch+4)(%esi), %esp + call 1f +1: popl %ebp + subl $ rva(1b), %ebp + + /* Load new GDT with the 64bit segments using 32bit descriptor */ + leal rva(gdt)(%ebp), %eax + movl %eax, 2(%eax) + lgdt (%eax) + + /* Load segment registers with our descriptors */ + movl $__BOOT_DS, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %fs + movl %eax, %gs + movl %eax, %ss + + /* Setup a stack and load CS from current GDT */ + leal rva(boot_stack_end)(%ebp), %esp + + pushl $__KERNEL32_CS + leal rva(1f)(%ebp), %eax + pushl %eax + lretl +1: + + /* Setup Exception handling for SEV-ES */ +#ifdef CONFIG_AMD_MEM_ENCRYPT + call startup32_load_idt +#endif + + /* Make sure cpu supports long mode. */ + call verify_cpu + testl %eax, %eax + jnz .Lno_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 + +#ifdef CONFIG_EFI_STUB +/* + * If we were loaded via the EFI LoadImage service, startup_32 will be at an + * offset to the start of the space allocated for the image. efi_pe_entry will + * set up image_offset to tell us where the image actually starts, so that we + * can use the full available buffer. + * image_offset = startup_32 - image_base + * Otherwise image_offset will be zero and has no effect on the calculations. + */ + subl rva(image_offset)(%ebp), %ebx +#endif + + movl BP_kernel_alignment(%esi), %eax + decl %eax + addl %eax, %ebx + notl %eax + andl %eax, %ebx + cmpl $LOAD_PHYSICAL_ADDR, %ebx + jae 1f +#endif + movl $LOAD_PHYSICAL_ADDR, %ebx +1: + + /* Target address to relocate to for decompression */ + addl BP_init_size(%esi), %ebx + subl $ rva(_end), %ebx + +/* + * Prepare for entering 64 bit mode + */ + + /* Enable PAE mode */ + movl %cr4, %eax + orl $X86_CR4_PAE, %eax + movl %eax, %cr4 + + /* + * Build early 4G boot pagetable + */ + /* + * If SEV is active then set the encryption mask in the page tables. + * This will ensure that when the kernel is copied and decompressed + * it will be done so encrypted. + */ + xorl %edx, %edx +#ifdef CONFIG_AMD_MEM_ENCRYPT + call get_sev_encryption_bit + xorl %edx, %edx + testl %eax, %eax + jz 1f + subl $32, %eax /* Encryption bit is always above bit 31 */ + bts %eax, %edx /* Set encryption mask for page tables */ + /* + * Set MSR_AMD64_SEV_ENABLED_BIT in sev_status so that + * startup32_check_sev_cbit() will do a check. sev_enable() will + * initialize sev_status with all the bits reported by + * MSR_AMD_SEV_STATUS later, but only MSR_AMD64_SEV_ENABLED_BIT + * needs to be set for now. + */ + movl $1, rva(sev_status)(%ebp) +1: +#endif + + /* Initialize Page tables to 0 */ + leal rva(pgtable)(%ebx), %edi + xorl %eax, %eax + movl $(BOOT_INIT_PGT_SIZE/4), %ecx + rep stosl + + /* Build Level 4 */ + leal rva(pgtable + 0)(%ebx), %edi + leal 0x1007 (%edi), %eax + movl %eax, 0(%edi) + addl %edx, 4(%edi) + + /* Build Level 3 */ + leal rva(pgtable + 0x1000)(%ebx), %edi + leal 0x1007(%edi), %eax + movl $4, %ecx +1: movl %eax, 0x00(%edi) + addl %edx, 0x04(%edi) + addl $0x00001000, %eax + addl $8, %edi + decl %ecx + jnz 1b + + /* Build Level 2 */ + leal rva(pgtable + 0x2000)(%ebx), %edi + movl $0x00000183, %eax + movl $2048, %ecx +1: movl %eax, 0(%edi) + addl %edx, 4(%edi) + addl $0x00200000, %eax + addl $8, %edi + decl %ecx + jnz 1b + + /* Enable the boot page tables */ + leal rva(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 + + /* After gdt is loaded */ + xorl %eax, %eax + lldt %ax + movl $__BOOT_TSS, %eax + ltr %ax + +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* Check if the C-bit position is correct when SEV is active */ + call startup32_check_sev_cbit +#endif + + /* + * Setup for the jump to 64bit mode + * + * When the jump is performed 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. + */ + leal rva(startup_64)(%ebp), %eax +#ifdef CONFIG_EFI_MIXED + cmpb $1, rva(efi_is64)(%ebp) + je 1f + leal rva(startup_64_mixed_mode)(%ebp), %eax +1: +#endif + + pushl $__KERNEL_CS + pushl %eax + + /* Enter paged protected Mode, activating Long Mode */ + movl $CR0_STATE, %eax + movl %eax, %cr0 + + /* Jump from 32bit compatibility mode into 64bit mode. */ + lret +SYM_FUNC_END(startup_32) + +#if IS_ENABLED(CONFIG_EFI_MIXED) && IS_ENABLED(CONFIG_EFI_HANDOVER_PROTOCOL) + .org 0x190 +SYM_FUNC_START(efi32_stub_entry) + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi + jmp efi32_entry +SYM_FUNC_END(efi32_stub_entry) +#endif + + .code64 + .org 0x200 +SYM_CODE_START(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, 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. + */ + + cld + cli + + /* Setup data segments. */ + xorl %eax, %eax + movl %eax, %ds + movl %eax, %es + movl %eax, %ss + movl %eax, %fs + movl %eax, %gs + + /* + * 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 LOAD_PHYSICAL_ADDR + * + * We cannot rely on the calculation done in 32-bit mode, since we + * may have been invoked via the 64-bit entry point. + */ + + /* Start with the delta to where the kernel will run at. */ +#ifdef CONFIG_RELOCATABLE + leaq startup_32(%rip) /* - $startup_32 */, %rbp + +#ifdef CONFIG_EFI_STUB +/* + * If we were loaded via the EFI LoadImage service, startup_32 will be at an + * offset to the start of the space allocated for the image. efi_pe_entry will + * set up image_offset to tell us where the image actually starts, so that we + * can use the full available buffer. + * image_offset = startup_32 - image_base + * Otherwise image_offset will be zero and has no effect on the calculations. + */ + movl image_offset(%rip), %eax + subq %rax, %rbp +#endif + + movl BP_kernel_alignment(%rsi), %eax + decl %eax + addq %rax, %rbp + notq %rax + andq %rax, %rbp + cmpq $LOAD_PHYSICAL_ADDR, %rbp + jae 1f +#endif + movq $LOAD_PHYSICAL_ADDR, %rbp +1: + + /* Target address to relocate to for decompression */ + movl BP_init_size(%rsi), %ebx + subl $ rva(_end), %ebx + addq %rbp, %rbx + + /* Set up the stack */ + leaq rva(boot_stack_end)(%rbx), %rsp + + /* + * At this point we are in long mode with 4-level paging enabled, + * but we might want to enable 5-level paging or vice versa. + * + * The problem is that we cannot do it directly. Setting or clearing + * CR4.LA57 in long mode would trigger #GP. So we need to switch off + * long mode and paging first. + * + * We also need a trampoline in lower memory to switch over from + * 4- to 5-level paging for cases when the bootloader puts the kernel + * above 4G, but didn't enable 5-level paging for us. + * + * The same trampoline can be used to switch from 5- to 4-level paging + * mode, like when starting 4-level paging kernel via kexec() when + * original kernel worked in 5-level paging mode. + * + * For the trampoline, we need the top page table to reside in lower + * memory as we don't have a way to load 64-bit values into CR3 in + * 32-bit mode. + * + * We go though the trampoline even if we don't have to: if we're + * already in a desired paging mode. This way the trampoline code gets + * tested on every boot. + */ + + /* Make sure we have GDT with 32-bit code segment */ + leaq gdt64(%rip), %rax + addq %rax, 2(%rax) + lgdt (%rax) + + /* Reload CS so IRET returns to a CS actually in the GDT */ + pushq $__KERNEL_CS + leaq .Lon_kernel_cs(%rip), %rax + pushq %rax + lretq + +.Lon_kernel_cs: + + pushq %rsi + call load_stage1_idt + popq %rsi + +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Now that the stage1 interrupt handlers are set up, #VC exceptions from + * CPUID instructions can be properly handled for SEV-ES guests. + * + * For SEV-SNP, the CPUID table also needs to be set up in advance of any + * CPUID instructions being issued, so go ahead and do that now via + * sev_enable(), which will also handle the rest of the SEV-related + * detection/setup to ensure that has been done in advance of any dependent + * code. + */ + pushq %rsi + movq %rsi, %rdi /* real mode address */ + call sev_enable + popq %rsi +#endif + + /* + * paging_prepare() sets up the trampoline and checks if we need to + * enable 5-level paging. + * + * paging_prepare() returns a two-quadword structure which lands + * into RDX:RAX: + * - Address of the trampoline is returned in RAX. + * - Non zero RDX means trampoline needs to enable 5-level + * paging. + * + * RSI holds real mode data and needs to be preserved across + * this function call. + */ + pushq %rsi + movq %rsi, %rdi /* real mode address */ + call paging_prepare + popq %rsi + + /* Save the trampoline address in RCX */ + movq %rax, %rcx + + /* + * Load the address of trampoline_return() into RDI. + * It will be used by the trampoline to return to the main code. + */ + leaq trampoline_return(%rip), %rdi + + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax + pushq %rax + lretq +trampoline_return: + /* Restore the stack, the 32-bit trampoline uses its own stack */ + leaq rva(boot_stack_end)(%rbx), %rsp + + /* + * cleanup_trampoline() would restore trampoline memory. + * + * RDI is address of the page table to use instead of page table + * in trampoline memory (if required). + * + * RSI holds real mode data and needs to be preserved across + * this function call. + */ + pushq %rsi + leaq rva(top_pgtable)(%rbx), %rdi + call cleanup_trampoline + popq %rsi + + /* Zero EFLAGS */ + pushq $0 + popfq + +/* + * Copy the compressed kernel to the end of our buffer + * where decompression in place becomes safe. + */ + pushq %rsi + leaq (_bss-8)(%rip), %rsi + leaq rva(_bss-8)(%rbx), %rdi + movl $(_bss - startup_32), %ecx + shrl $3, %ecx + std + rep movsq + cld + popq %rsi + + /* + * The GDT may get overwritten either during the copy we just did or + * during extract_kernel below. To avoid any issues, repoint the GDTR + * to the new copy of the GDT. + */ + leaq rva(gdt64)(%rbx), %rax + leaq rva(gdt)(%rbx), %rdx + movq %rdx, 2(%rax) + lgdt (%rax) + +/* + * Jump to the relocated address. + */ + leaq rva(.Lrelocated)(%rbx), %rax + jmp *%rax +SYM_CODE_END(startup_64) + +#ifdef CONFIG_EFI_STUB +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + .org 0x390 +#endif +SYM_FUNC_START(efi64_stub_entry) + and $~0xf, %rsp /* realign the stack */ + movq %rdx, %rbx /* save boot_params pointer */ + call efi_main + movq %rbx,%rsi + leaq rva(startup_64)(%rax), %rax + jmp *%rax +SYM_FUNC_END(efi64_stub_entry) +SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry) +#endif + + .text +SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) + +/* + * Clear BSS (stack is currently empty) + */ + xorl %eax, %eax + leaq _bss(%rip), %rdi + leaq _ebss(%rip), %rcx + subq %rdi, %rcx + shrq $3, %rcx + rep stosq + + pushq %rsi + call load_stage2_idt + + /* Pass boot_params to initialize_identity_maps() */ + movq (%rsp), %rdi + call initialize_identity_maps + popq %rsi + +/* + * Do the extraction, and jump to the new kernel.. + */ + pushq %rsi /* Save the real mode argument */ + movq %rsi, %rdi /* real mode address */ + leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ + leaq input_data(%rip), %rdx /* input_data */ + movl input_len(%rip), %ecx /* input_len */ + movq %rbp, %r8 /* output target address */ + movl output_len(%rip), %r9d /* decompressed length, end of relocs */ + call extract_kernel /* returns kernel entry point in %rax */ + popq %rsi + +/* + * Jump to the decompressed kernel. + */ + jmp *%rax +SYM_FUNC_END(.Lrelocated) + + .code32 +/* + * This is the 32-bit trampoline that will be copied over to low memory. + * + * RDI contains the return address (might be above 4G). + * ECX contains the base address of the trampoline memory. + * Non zero RDX means trampoline needs to enable 5-level paging. + */ +SYM_CODE_START(trampoline_32bit_src) + /* Set up data and stack segments */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %ss + + /* Set up new stack */ + leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Check what paging mode we want to be in after the trampoline */ + testl %edx, %edx + jz 1f + + /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ + movl %cr4, %eax + testl $X86_CR4_LA57, %eax + jnz 3f + jmp 2f +1: + /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ + movl %cr4, %eax + testl $X86_CR4_LA57, %eax + jz 3f +2: + /* Point CR3 to the trampoline's new top level page table */ + leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax + movl %eax, %cr3 +3: + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ + pushl %ecx + pushl %edx + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + /* Avoid writing EFER if no change was made (for TDX guest) */ + jc 1f + wrmsr +1: popl %edx + popl %ecx + +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movl %cr4, %eax + andl $X86_CR4_MCE, %eax +#else + movl $0, %eax +#endif + + /* Enable PAE and LA57 (if required) paging modes */ + orl $X86_CR4_PAE, %eax + testl %edx, %edx + jz 1f + orl $X86_CR4_LA57, %eax +1: + movl %eax, %cr4 + + /* Calculate address of paging_enabled() once we are executing in the trampoline */ + leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax + + /* Prepare the stack for far return to Long Mode */ + pushl $__KERNEL_CS + pushl %eax + + /* Enable paging again. */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + lret +SYM_CODE_END(trampoline_32bit_src) + + .code64 +SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) + /* Return from the trampoline */ + jmp *%rdi +SYM_FUNC_END(.Lpaging_enabled) + + /* + * The trampoline code has a size limit. + * Make sure we fail to compile if the trampoline code grows + * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes. + */ + .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE + + .code32 +SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) + /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ +1: + hlt + jmp 1b +SYM_FUNC_END(.Lno_longmode) + + .globl verify_cpu +#include "../../kernel/verify_cpu.S" + + .data +SYM_DATA_START_LOCAL(gdt64) + .word gdt_end - gdt - 1 + .quad gdt - gdt64 +SYM_DATA_END(gdt64) + .balign 8 +SYM_DATA_START_LOCAL(gdt) + .word gdt_end - gdt - 1 + .long 0 + .word 0 + .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ + .quad 0x00af9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf92000000ffff /* __KERNEL_DS */ + .quad 0x0080890000000000 /* TS descriptor */ + .quad 0x0000000000000000 /* TS continued */ +SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) + +SYM_DATA_START(boot_idt_desc) + .word boot_idt_end - boot_idt - 1 + .quad 0 +SYM_DATA_END(boot_idt_desc) + .balign 8 +SYM_DATA_START(boot_idt) + .rept BOOT_IDT_ENTRIES + .quad 0 + .quad 0 + .endr +SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) + +/* + * Stack and heap for uncompression + */ + .bss + .balign 4 +SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) + +SYM_DATA_START_LOCAL(boot_stack) + .fill BOOT_STACK_SIZE, 1, 0 + .balign 16 +SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) + +/* + * Space for page tables (not in .bss so not zeroed) + */ + .section ".pgtable","aw",@nobits + .balign 4096 +SYM_DATA_LOCAL(pgtable, .fill BOOT_PGT_SIZE, 1, 0) + +/* + * The page table is going to be used instead of page table in the trampoline + * memory. + */ +SYM_DATA_LOCAL(top_pgtable, .fill PAGE_SIZE, 1, 0) |