linux_dsm_epyc7002/arch/x86/boot/compressed/head_64.S
Kirill A. Shutemov 08529078d8 x86/boot/compressed/64: Detect and handle 5-level paging at boot-time
Prerequisite for fixing the current problem of instantaneous reboots when a
5-level paging kernel is booted on 4-level paging hardware.

At the same time this change prepares the decompression code to boot-time
switching between 4- and 5-level paging.

[ tglx: Folded the GCC < 5 fix. ]

Fixes: 77ef56e4f0 ("x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: stable@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: linux-mm@kvack.org
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20171204124059.63515-2-kirill.shutemov@linux.intel.com
2017-12-07 10:34:39 +01:00

592 lines
12 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>
/*
* 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
#ifdef CONFIG_X86_5LEVEL
/*
* Check if we need to enable 5-level paging.
* RSI holds real mode data and need to be preserved across
* a function call.
*/
pushq %rsi
call l5_paging_required
popq %rsi
/* If l5_paging_required() returned zero, we're done here. */
cmpq $0, %rax
je lvl5
/*
* At this point we are in long mode with 4-level paging enabled,
* but we want to enable 5-level paging.
*
* The problem is that we cannot do it directly. Setting LA57 in
* long mode would trigger #GP. So we need to switch off long mode
* first.
*
* NOTE: This is not going to work if bootloader put us above 4G
* limit.
*
* The first step is go into compatibility mode.
*/
/* Clear additional page table */
leaq lvl5_pgtable(%rbx), %rdi
xorq %rax, %rax
movq $(PAGE_SIZE/8), %rcx
rep stosq
/*
* Setup current CR3 as the first and only entry in a new top level
* page table.
*/
movq %cr3, %rdi
leaq 0x7 (%rdi), %rax
movq %rax, lvl5_pgtable(%rbx)
/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
pushq $__KERNEL32_CS
leaq compatible_mode(%rip), %rax
pushq %rax
lretq
lvl5:
#endif
/* 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 (_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
/*
* Adjust our own GOT
*/
leaq _got(%rip), %rdx
leaq _egot(%rip), %rcx
1:
cmpq %rcx, %rdx
jae 2f
addq %rbx, (%rdx)
addq $8, %rdx
jmp 1b
2:
/*
* 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
.code32
#ifdef CONFIG_X86_5LEVEL
compatible_mode:
/* Setup data and stack segments */
movl $__KERNEL_DS, %eax
movl %eax, %ds
movl %eax, %ss
/* Disable paging */
movl %cr0, %eax
btrl $X86_CR0_PG_BIT, %eax
movl %eax, %cr0
/* Point CR3 to 5-level paging */
leal lvl5_pgtable(%ebx), %eax
movl %eax, %cr3
/* Enable PAE and LA57 mode */
movl %cr4, %eax
orl $(X86_CR4_PAE | X86_CR4_LA57), %eax
movl %eax, %cr4
/* Calculate address we are running at */
call 1f
1: popl %edi
subl $1b, %edi
/* Prepare stack for far return to Long Mode */
pushl $__KERNEL_CS
leal lvl5(%edi), %eax
push %eax
/* Enable paging back */
movl $(X86_CR0_PG | X86_CR0_PE), %eax
movl %eax, %cr0
lret
#endif
no_longmode:
/* This isn't an x86-64 CPU so hang */
1:
hlt
jmp 1b
#include "../../kernel/verify_cpu.S"
.data
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
#ifdef CONFIG_X86_5LEVEL
lvl5_pgtable:
.fill PAGE_SIZE, 1, 0
#endif