linux/arch/x86/boot/compressed/head_64.S
Kirill A. Shutemov 372fddf709 x86/mm: Introduce the 'no5lvl' kernel parameter
This kernel parameter allows to force kernel to use 4-level paging even
if hardware and kernel support 5-level paging.

The option may be useful to work around regressions related to 5-level
paging.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180518103528.59260-5-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-05-19 11:56:57 +02:00

706 lines
16 KiB
ArmAsm

/* 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 "pgtable.h"
/*
* Locally defined symbols should be marked hidden:
*/
.hidden _bss
.hidden _ebss
.hidden _got
.hidden _egot
__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
* us to not reload segments
*/
testb $KEEP_SEGMENTS, BP_loadflags(%esi)
jnz 1f
cli
movl $(__BOOT_DS), %eax
movl %eax, %ds
movl %eax, %es
movl %eax, %ss
1:
/*
* 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 $1b, %ebp
/* setup a stack and make sure cpu supports long mode. */
movl $boot_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
movl BP_kernel_alignment(%esi), %eax
decl %eax
addl %eax, %ebx
notl %eax
andl %eax, %ebx
cmpl $LOAD_PHYSICAL_ADDR, %ebx
jge 1f
#endif
movl $LOAD_PHYSICAL_ADDR, %ebx
1:
/* Target address to relocate to for decompression */
movl BP_init_size(%esi), %eax
subl $_end, %eax
addl %eax, %ebx
/*
* Prepare for entering 64 bit mode
*/
/* Load new GDT with the 64bit segments using 32bit descriptor */
addl %ebp, gdt+2(%ebp)
lgdt gdt(%ebp)
/* 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 insure that when the kernel is copied and decompressed
* it will be done so encrypted.
*/
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 */
1:
/* Initialize Page tables to 0 */
leal pgtable(%ebx), %edi
xorl %eax, %eax
movl $(BOOT_INIT_PGT_SIZE/4), %ecx
rep stosl
/* Build Level 4 */
leal pgtable + 0(%ebx), %edi
leal 0x1007 (%edi), %eax
movl %eax, 0(%edi)
addl %edx, 4(%edi)
/* Build Level 3 */
leal 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 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 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
/*
* 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
#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 */
movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
movl %eax, %cr0
/* Jump from 32bit compatibility mode into 64bit mode. */
lret
ENDPROC(startup_32)
#ifdef CONFIG_EFI_MIXED
.org 0x190
ENTRY(efi32_stub_entry)
add $0x4, %esp /* Discard return address */
popl %ecx
popl %edx
popl %esi
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
.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, 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.
*/
/* 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
movl BP_kernel_alignment(%rsi), %eax
decl %eax
addq %rax, %rbp
notq %rax
andq %rax, %rbp
cmpq $LOAD_PHYSICAL_ADDR, %rbp
jge 1f
#endif
movq $LOAD_PHYSICAL_ADDR, %rbp
1:
/* Target address to relocate to for decompression */
movl BP_init_size(%rsi), %ebx
subl $_end, %ebx
addq %rbp, %rbx
/* Set up the stack */
leaq boot_stack_end(%rbx), %rsp
/*
* paging_prepare() and cleanup_trampoline() below can have GOT
* references. Adjust the table with address we are running at.
*
* Zero RAX for adjust_got: the GOT was not adjusted before;
* there's no adjustment to undo.
*/
xorq %rax, %rax
/*
* Calculate the address the binary is loaded at and use it as
* a GOT adjustment.
*/
call 1f
1: popq %rdi
subq $1b, %rdi
call adjust_got
/*
* 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 gdt(%rip), %rax
movq %rax, gdt64+2(%rip)
lgdt gdt64(%rip)
/*
* paging_prepare() sets up the trampoline and checks if we need to
* enable 5-level paging.
*
* Address of the trampoline is returned in RAX.
* Non zero RDX on return means we need 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 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 top_pgtable(%rbx), %rdi
call cleanup_trampoline
popq %rsi
/* Zero EFLAGS */
pushq $0
popfq
/*
* Previously we've adjusted the GOT with address the binary was
* loaded at. Now we need to re-adjust for relocation address.
*
* Calculate the address the binary is loaded at, so that we can
* undo the previous GOT adjustment.
*/
call 1f
1: popq %rax
subq $1b, %rax
/* The new adjustment is the relocation address */
movq %rbx, %rdi
call adjust_got
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
*/
pushq %rsi
leaq (_bss-8)(%rip), %rsi
leaq (_bss-8)(%rbx), %rdi
movq $_bss /* - $startup_32 */, %rcx
shrq $3, %rcx
std
rep movsq
cld
popq %rsi
/*
* Jump to the relocated address.
*/
leaq relocated(%rbx), %rax
jmp *%rax
#ifdef CONFIG_EFI_STUB
/* The entry point for the PE/COFF executable is efi_pe_entry. */
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+40(%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, 40(%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 startup_64(%rax), %rax
jmp *%rax
ENDPROC(efi_pe_entry)
.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:
/*
* 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
/*
* 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 $z_input_len, %ecx /* input_len */
movq %rbp, %r8 /* output target address */
movq $z_output_len, %r9 /* decompressed length, end of relocs */
call extract_kernel /* returns kernel location in %rax */
popq %rsi
/*
* Jump to the decompressed kernel.
*/
jmp *%rax
/*
* Adjust the global offset table
*
* RAX is the previous adjustment of the table to undo (use 0 if it's the
* first time we touch GOT).
* RDI is the new adjustment to apply.
*/
adjust_got:
/* Walk through the GOT adding the address to the entries */
leaq _got(%rip), %rdx
leaq _egot(%rip), %rcx
1:
cmpq %rcx, %rdx
jae 2f
subq %rax, (%rdx) /* Undo previous adjustment */
addq %rdi, (%rdx) /* Apply the new adjustment */
addq $8, %rdx
jmp 1b
2:
ret
.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 on return means we need to enable 5-level paging.
*/
ENTRY(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 */
cmpl $0, %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:
/* Enable PAE and LA57 (if required) paging modes */
movl $X86_CR4_PAE, %eax
cmpl $0, %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 paging_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 $(X86_CR0_PG | X86_CR0_PE), %eax
movl %eax, %cr0
lret
.code64
paging_enabled:
/* Return from the trampoline */
jmp *%rdi
/*
* 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
no_longmode:
/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
1:
hlt
jmp 1b
#include "../../kernel/verify_cpu.S"
.data
gdt64:
.word gdt_end - gdt
.long 0
.word 0
.quad 0
gdt:
.word gdt_end - gdt
.long gdt
.word 0
.quad 0x00cf9a000000ffff /* __KERNEL32_CS */
.quad 0x00af9a000000ffff /* __KERNEL_CS */
.quad 0x00cf92000000ffff /* __KERNEL_DS */
.quad 0x0080890000000000 /* TS descriptor */
.quad 0x0000000000000000 /* TS continued */
gdt_end:
#ifdef CONFIG_EFI_STUB
efi_config:
.quad 0
#ifdef CONFIG_EFI_MIXED
.global efi32_config
efi32_config:
.fill 5,8,0
.quad efi64_thunk
.byte 0
#endif
.global efi64_config
efi64_config:
.fill 5,8,0
.quad efi_call
.byte 1
#endif /* CONFIG_EFI_STUB */
/*
* Stack and heap for uncompression
*/
.bss
.balign 4
boot_heap:
.fill BOOT_HEAP_SIZE, 1, 0
boot_stack:
.fill BOOT_STACK_SIZE, 1, 0
boot_stack_end:
/*
* Space for page tables (not in .bss so not zeroed)
*/
.section ".pgtable","a",@nobits
.balign 4096
pgtable:
.fill BOOT_PGT_SIZE, 1, 0
/*
* The page table is going to be used instead of page table in the trampoline
* memory.
*/
top_pgtable:
.fill PAGE_SIZE, 1, 0